© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 73433
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
     어느
    -0.07
     vyšší
    -0.07
     ROW
    -0.07
     pushing
    -0.07
     misdemean
    -0.06
    sector
    -0.06
     Yük
    -0.06
    ’é
    -0.06
     divorce
    -0.06
    шив
    -0.06
    POSITIVE LOGITS
     correo
    0.06
     TITLE
    0.06
    ۳۶
    0.06
     §§
    0.06
     trot
    0.06
    Curr
    0.06
    笔
    0.06
    XX
    0.06
    英雄
    0.06
    WND
    0.05
    Activations Density 0.015%

    No Known Activations