© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129949
    Prev
    Next
    INDEX
    Explanations

    informal language

    np_max-act · gemini-2.0-flash

    scenarios or statements that involve gender-related themes or issues.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    This neuron detects the special “<|start_header_id|>” token that marks the start of a message header (i.e. the beginning of a new chat turn).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    vocabulary related to formal attire, particularly for women in a professional context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cyn
    -0.07
     Genius
    -0.07
     preparation
    -0.07
    EMA
    -0.07
     prepar
    -0.07
     compounded
    -0.06
     numerator
    -0.06
    Avg
    -0.06
    ($
    -0.06
     aspect
    -0.06
    POSITIVE LOGITS
    .Ext
    0.06
    .setHeader
    0.06
     PARTY
    0.06
    _argv
    0.06
    -functional
    0.06
     Bridges
    0.06
     Carlo
    0.05
    damn
    0.05
    Sphere
    0.05
     możli
    0.05
    Activations Density 0.062%

    No Known Activations