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. 109943
    Prev
    Next
    INDEX
    Explanations

    names

    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
     Daughter
    -0.08
    ‌آ
    -0.07
    008
    -0.07
     <!--[
    -0.07
     suspected
    -0.06
     SRC
    -0.06
     Hearts
    -0.06
     shortened
    -0.06
     Cor
    -0.06
    rgctx
    -0.06
    POSITIVE LOGITS
    _DURATION
    0.06
     varsa
    0.06
    _nonce
    0.06
    (abs
    0.06
     такі
    0.06
    .getOrder
    0.06
     губ
    0.06
    EV
    0.06
     rast
    0.06
    _delay
    0.05
    Activations Density 0.016%

    No Known Activations