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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RESID-POST-AA
    6. 75050
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Links
    -0.07
    ераль
    -0.07
    억
    -0.06
    期间
    -0.06
     Match
    -0.06
    وپ
    -0.06
     ay
    -0.06
     routine
    -0.06
    ΑΡ
    -0.06
    ille
    -0.06
    POSITIVE LOGITS
    chars
    0.07
    '↵↵↵
    0.07
    .↵↵↵↵
    0.07
     Лит
    0.07
    PCODE
    0.07
     cosas
    0.06
    JSONException
    0.06
     dejar
    0.06
    unit
    0.06
     monet
    0.06
    Activations Density 0.078%

    No Known Activations