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. 15-RESID-POST-AA
    6. 80828
    Prev
    Next
    INDEX
    Explanations

    problems, uncertainties

    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
     steht
    -0.08
     Comes
    -0.07
    ail
    -0.07
    Any
    -0.06
    .Any
    -0.06
    berman
    -0.06
    .complete
    -0.06
    toList
    -0.06
    -elected
    -0.06
     ngừng
    -0.06
    POSITIVE LOGITS
     Pun
    0.07
    enties
    0.06
     Luật
    0.06
     Aleppo
    0.06
    舗
    0.06
     köy
    0.06
     mnemonic
    0.06
    terra
    0.06
     mime
    0.06
     att
    0.06
    Activations Density 0.262%

    No Known Activations