© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 113568
    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_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
    .beh
    -0.07
    نب
    -0.06
    pose
    -0.06
    เซ
    -0.06
    loser
    -0.06
    za
    -0.06
     striker
    -0.06
    籍
    -0.06
    'h
    -0.06
     возраста
    -0.06
    POSITIVE LOGITS
    /operator
    0.07
     handlers
    0.06
    Deadline
    0.06
    InOut
    0.06
    unched
    0.06
    _sock
    0.06
    _BUF
    0.06
    +</
    0.06
    _rgba
    0.06
     Buccane
    0.06
    Activations Density 0.003%

    No Known Activations