© 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. 72836
    Prev
    Next
    INDEX
    Explanations

    mathematical/scientific text

    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
    .var
    -0.07
    Err
    -0.06
    XL
    -0.06
     Cohen
    -0.06
    [attr
    -0.06
     품
    -0.06
    .src
    -0.06
     Cambodia
    -0.06
    110
    -0.06
     topp
    -0.06
    POSITIVE LOGITS
    Explicit
    0.08
     Explicit
    0.06
     jump
    0.06
     lucky
    0.06
     może
    0.06
     и
    0.06
    .Monad
    0.06
    ×
    0.06
    	distance
    0.06
     solution
    0.06
    Activations Density 0.014%

    No Known Activations