© 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. 93589
    Prev
    Next
    INDEX
    Explanations

    fool

    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
    xyz
    -0.06
     Joshua
    -0.06
     deltaY
    -0.06
    _repository
    -0.06
     grains
    -0.06
    орот
    -0.06
    縣
    -0.06
    -network
    -0.06
    argins
    -0.06
    ;
↵
↵
↵
    -0.06
    POSITIVE LOGITS
     fool
    0.11
     fooled
    0.09
     fools
    0.09
     foolish
    0.08
     Fool
    0.08
    喜
    0.07
    .pkl
    0.06
    сим
    0.06
    .setModel
    0.06
    วม
    0.06
    Activations Density 0.002%

    No Known Activations