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. 112747
    Prev
    Next
    INDEX
    Explanations

    in

    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
    919
    -0.06
    форм
    -0.06
     �
    -0.06
     filters
    -0.06
     dyst
    -0.06
    314
    -0.06
    .timestamp
    -0.06
     Firm
    -0.06
    πουργ
    -0.06
    μένα
    -0.06
    POSITIVE LOGITS
     small
    0.06
    .rev
    0.06
    indered
    0.06
     крит
    0.06
     thinner
    0.06
     auditory
    0.06
    =UTF
    0.06
     surprises
    0.06
    .sulake
    0.06
    益
    0.06
    Activations Density 0.000%

    No Known Activations