© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 36962
    Prev
    Next
    INDEX
    Explanations

    Repetition and keeping customers

    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
     rút
    -0.08
     argparse
    -0.06
    _timeout
    -0.06
    itions
    -0.06
    ，大
    -0.06
    嫌
    -0.06
    提供
    -0.06
    408
    -0.06
    ığ
    -0.06
     몇
    -0.06
    POSITIVE LOGITS
    Easy
    0.07
     diabetes
    0.07
    tm
    0.06
    Comm
    0.06
    _BLEND
    0.06
     Convenience
    0.06
     LICENSE
    0.06
     SPACE
    0.06
    _ac
    0.06
     sincerely
    0.06
    Activations Density 0.016%

    No Known Activations