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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RESID-POST-AA
    6. 95495
    Prev
    Next
    INDEX
    Explanations

    asterisk

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betr
    -0.07
     therapy
    -0.06
     Battlefield
    -0.06
    (hr
    -0.06
    amm
    -0.06
     {
    -0.06
    [h
    -0.06
     정치
    -0.06
     такі
    -0.06
     Worksheet
    -0.06
    POSITIVE LOGITS
    *↵
    0.07
    ?>"/>↵
    0.07
    Japanese
    0.06
     absorbs
    0.06
    bob
    0.06
    051
    0.06
     @"↵
    0.06
     Ngân
    0.06
    .PictureBoxSizeMode
    0.06
    641
    0.06
    Activations Density 0.018%

    No Known Activations