© 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. 27630
    Prev
    Next
    INDEX
    Explanations

    Creativity and interpretation

    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
    _sim
    -0.07
     serviço
    -0.07
     supportive
    -0.06
    CAM
    -0.06
    �
    -0.06
     tức
    -0.06
    usband
    -0.06
     toy
    -0.06
     робота
    -0.06
     crate
    -0.06
    POSITIVE LOGITS
     전용
    0.07
     Anna
    0.07
     parms
    0.07
    .setCursor
    0.07
     ICT
    0.07
     inaug
    0.06
     Drawable
    0.06
    _TRANSFORM
    0.06
    +='<
    0.06
     //</
    0.06
    Activations Density 0.080%

    No Known Activations