© 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. 11-RESID-POST-AA
    11. 35018
    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
    TRL
    -0.07
    Printing
    -0.06
    Threshold
    -0.06
    력
    -0.06
    lichen
    -0.06
     Language
    -0.06
    History
    -0.06
    _supply
    -0.06
     Provid
    -0.06
    toBeFalsy
    -0.06
    POSITIVE LOGITS
    นาย
    0.08
     Hait
    0.07
     femin
    0.06
     meng
    0.06
    .money
    0.06
    驱
    0.06
     russ
    0.06
     impaired
    0.06
     chmod
    0.06
    >",↵
    0.06
    Activations Density 0.003%

    No Known Activations