© 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. 19-RESID-POST-AA
    11. 124885
    Prev
    Next
    INDEX
    Explanations

    Unwanted touching

    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
    outs
    -0.08
    amide
    -0.07
    @g
    -0.06
    INO
    -0.06
     durante
    -0.06
    oun
    -0.06
     mice
    -0.06
    UT
    -0.06
    iders
    -0.06
     Westminster
    -0.06
    POSITIVE LOGITS
    elloworld
    0.08
     đường
    0.07
     '[
    0.06
     Qualcomm
    0.06
    (parseInt
    0.06
    genden
    0.06
     coercion
    0.06
    .Endpoint
    0.06
     ExecutionContext
    0.06
    ॰
    0.06
    Activations Density 0.093%

    No Known Activations