© 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. 100032
    Prev
    Next
    INDEX
    Explanations

    brain/nervous system

    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
     dishes
    -0.07
     @{@"
    -0.07
    ullen
    -0.07
     Buff
    -0.06
    extView
    -0.06
     impulse
    -0.06
     scoop
    -0.06
    Lua
    -0.06
    円
    -0.06
     tourist
    -0.06
    POSITIVE LOGITS
     về
    0.06
     kayb
    0.06
     evolves
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Iss
    0.06
     önemli
    0.06
     Pick
    0.06
    _interrupt
    0.06
    ivement
    0.06
    .FC
    0.06
    Activations Density 0.018%

    No Known Activations