© 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. 56227
    Prev
    Next
    INDEX
    Explanations

    Alphanumeric IDs or codes

    np_max-act · gemini-2.0-flash

    The neuron fires on table‐style alphanumeric codes (short tokens mixing uppercase letters and digits) such as “DW,” “EG,” “AP4,” etc.

    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
    出口
    -0.07
     Kop
    -0.07
    _DUMP
    -0.06
     pops
    -0.06
    cee
    -0.06
    defaultValue
    -0.06
     العامة
    -0.06
    _problem
    -0.06
     Deletes
    -0.06
     Revenge
    -0.06
    POSITIVE LOGITS
    主义
    0.06
    tesy
    0.06
    ,更
    0.06
     Malone
    0.06
    ,同时
    0.06
     أك
    0.06
    abez
    0.05
     youngest
    0.05
    .Property
    0.05
     багат
    0.05
    Activations Density 0.037%

    No Known Activations