© 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. 19-RESID-POST-AA
    11. 111731
    Prev
    Next
    INDEX
    Explanations

    inson

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     культу
    -0.06
     hect
    -0.06
    	assertTrue
    -0.06
     scraped
    -0.06
     cultured
    -0.06
     parsed
    -0.06
    Carol
    -0.06
    ']+
    -0.06
     Narrow
    -0.06
    _circle
    -0.06
    POSITIVE LOGITS
     Robinson
    0.11
    egrator
    0.07
    connector
    0.07
    iples
    0.07
     commissioner
    0.07
     Sutton
    0.07
    ooter
    0.07
    igger
    0.07
    ●
    0.07
    activ
    0.07
    Activations Density 0.002%

    No Known Activations