© 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. 68465
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    code snippets and commands related to programming, particularly in scripting and configuration.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on code identifiers—especially variable or parameter names (including mixed‐case or underscore‐separated names).

    oai_token-act-pair · o4-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
    .daily
    -0.06
     goof
    -0.06
    			     
    -0.06
    ane
    -0.06
    صت
    -0.06
     negotiating
    -0.06
     mediation
    -0.06
     과정
    -0.06
    違い
    -0.06
     Centers
    -0.06
    POSITIVE LOGITS
     tipos
    0.07
    Style
    0.07
    _bo
    0.06
     endDate
    0.06
    izione
    0.06
     Trab
    0.06
     cpt
    0.06
     мен
    0.06
     sher
    0.06
    RS
    0.06
    Activations Density 0.012%

    No Known Activations