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. 80989
    Prev
    Next
    INDEX
    Explanations

    dismiss

    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
     tạo
    -0.06
     std
    -0.06
    樹
    -0.06
     phen
    -0.06
    心理
    -0.06
    RN
    -0.06
    rá
    -0.06
     důsled
    -0.06
     santé
    -0.06
    へと
    -0.06
    POSITIVE LOGITS
     dismissed
    0.08
    Miss
    0.08
    Mitch
    0.07
     MISS
    0.07
    ORIGINAL
    0.07
    τική
    0.07
    (timer
    0.07
    inston
    0.07
    ,...
    0.07
     dismissal
    0.07
    Activations Density 0.004%

    No Known Activations