© 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. 94132
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    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
    cline
    -0.07
    ứa
    -0.07
     persuasive
    -0.07
    _per
    -0.06
    .employee
    -0.06
     незалеж
    -0.06
    登録
    -0.06
    frican
    -0.06
     imprisonment
    -0.06
     Sesso
    -0.06
    POSITIVE LOGITS
    (fileName
    0.06
    数
    0.06
    NAL
    0.06
    lique
    0.06
     ah
    0.06
    )'↵
    0.06
     lat
    0.06
     canned
    0.06
     renovations
    0.06
     террит
    0.06
    Activations Density 0.038%

    No Known Activations