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

    Neuronpedia

    APICircuit 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. 81066
    Prev
    Next
    INDEX
    Explanations

    Descriptive passages

    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
    .mix
    -0.07
    .utf
    -0.07
    elocity
    -0.07
     roaring
    -0.07
    .CG
    -0.06
     tobacco
    -0.06
    _csv
    -0.06
    -shaped
    -0.06
    BinContent
    -0.06
     balancing
    -0.06
    POSITIVE LOGITS
    πος
    0.07
     lawful
    0.06
     unrestricted
    0.06
    omaly
    0.06
     مشکل
    0.06
     ters
    0.06
     intrusive
    0.06
    整个
    0.06
     milfs
    0.06
    详
    0.06
    Activations Density 0.046%

    No Known Activations