© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41349
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    HTML tags and structural elements in a web document.

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

    This neuron detects HTML navigation/menu structures (e.g. nav, ul/li lists of links with href or class attributes).

    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
     Clip
    -0.07
    clause
    -0.07
    CU
    -0.07
     charges
    -0.07
    evaluate
    -0.06
    教学
    -0.06
    旋
    -0.06
    佐
    -0.06
     stereotypes
    -0.06
    Enemies
    -0.06
    POSITIVE LOGITS
    .labelControl
    0.06
     Fires
    0.06
    -line
    0.06
     transmissions
    0.05
    raries
    0.05
     defaulted
    0.05
     использ
    0.05
     것은
    0.05
    0.05
     //}↵↵
    0.05
    Activations Density 0.013%

    No Known Activations