© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 22451
    Prev
    Next
    INDEX
    Explanations

    Code

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ání
    -0.07
    ／
    -0.07
     bütün
    -0.07
    Hay
    -0.07
     devotion
    -0.06
    ​
    -0.06
    ático
    -0.06
     Hugo
    -0.06
     Hay
    -0.06
     Sü
    -0.06
    POSITIVE LOGITS
    ('.')[
    0.07
    говор
    0.07
    Binary
    0.07
    -controlled
    0.06
    -value
    0.06
    Each
    0.06
     Tah
    0.06
    รก
    0.06
    .Claims
    0.06
    _LONG
    0.06
    Activations Density 0.002%

    No Known Activations