Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 54321
    Prev
    Next
    INDEX
    Explanations

    github

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Рад
    -0.07
     coch
    -0.07
     accept
    -0.07
    ')?>
    -0.06
    jící
    -0.06
     май
    -0.06
    Sw
    -0.06
    ())
    ↵
    -0.06
    Điều
    -0.06
                                                                                       
    -0.06
    POSITIVE LOGITS
    .vn
    0.07
    DV
    0.06
    syntax
    0.06
     aftermath
    0.06
    @SuppressWarnings
    0.06
     */
    ↵
    ↵
    0.06
    ,V
    0.06
    pawn
    0.06
     Tanz
    0.06
     Bibli
    0.06
    Activations Density 0.001%

    No Known Activations