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. 15-RESID-POST-AA
    6. 37258
    Prev
    Next
    INDEX
    Explanations

    her

    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
     květ
    -0.07
     desta
    -0.06
    .พ
    -0.06
     JButton
    -0.06
     ".";↵
    -0.06
    aría
    -0.06
    _since
    -0.06
    beta
    -0.06
     ^{↵
    -0.06
     Feder
    -0.06
    POSITIVE LOGITS
     checkpoint
    0.07
    .choose
    0.06
    (prefix
    0.06
    Getting
    0.06
     згідно
    0.06
     issues
    0.06
     choose
    0.06
    Intialized
    0.06
     commuting
    0.06
     harmonic
    0.06
    Activations Density 0.000%

    No Known Activations