© 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. 88175
    Prev
    Next
    INDEX
    Explanations

    Parts/sections/installments

    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
     numpy
    -0.07
    peace
    -0.07
     См
    -0.06
     szer
    -0.06
    enc
    -0.06
     /
    -0.06
     Wood
    -0.06
     Forest
    -0.06
    .NONE
    -0.06
     Noir
    -0.06
    POSITIVE LOGITS
    _BITMAP
    0.07
    )a
    0.07
     cyan
    0.07
    TimeZone
    0.07
     mip
    0.07
    енности
    0.06
    �
    0.06
     челов
    0.06
    _Al
    0.06
     librarian
    0.06
    Activations Density 0.019%

    No Known Activations