Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 123230
    Prev
    Next
    INDEX
    Explanations

    )

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAV
    -0.07
    Radio
    -0.07
     incididunt
    -0.06
     αντι
    -0.06
     Trend
    -0.06
    ry
    -0.06
     Nowadays
    -0.06
    <unsigned
    -0.06
     ticker
    -0.06
    Merc
    -0.06
    POSITIVE LOGITS
    _CF
    0.07
    отя
    0.07
    ेष
    0.07
     resetting
    0.07
     smashing
    0.06
    icas
    0.06
    .references
    0.06
     проведення
    0.06
    انون
    0.06
     bearing
    0.06
    Activations Density 0.008%

    No Known Activations