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. 11-RESID-POST-AA
    6. 84376
    Prev
    Next
    INDEX
    Explanations

    E

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zag
    -0.06
    ached
    -0.06
    bases
    -0.06
    Shift
    -0.06
     Send
    -0.06
     cil
    -0.06
    ampp
    -0.06
    chg
    -0.06
     Villa
    -0.06
     deviations
    -0.06
    POSITIVE LOGITS
    GRA
    0.07
    信用
    0.07
     rež
    0.07
     υπάρχ
    0.06
    FEATURE
    0.06
    _received
    0.06
     мот
    0.06
     SERIAL
    0.06
     broaden
    0.06
     объек
    0.06
    Activations Density 0.006%

    No Known Activations