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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 63527
    Prev
    Next
    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash

    mentions of specific quantitative details (percentages, dates, amounts) and formal institutional or technical terms in informational text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luví
    -0.07
     JADX
    -0.07
     Cards
    -0.06
    满
    -0.06
    .SEVERE
    -0.06
     ********************************************************
    -0.06
    _sync
    -0.06
    QP
    -0.06
    Repositories
    -0.06
    HasColumnType
    -0.06
    POSITIVE LOGITS
    <count
    0.07
     GraphQL
    0.07
    	rc
    0.06
    _SEG
    0.06
     brethren
    0.06
     camel
    0.06
     vole
    0.06
     presumably
    0.06
    chron
    0.06
     SEN
    0.06
    Activations Density 0.925%

    No Known Activations