© 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. 109268
    Prev
    Next
    INDEX
    Explanations

    conclude

    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
     alın
    -0.08
    >You
    -0.07
    Remarks
    -0.06
     Ford
    -0.06
    seat
    -0.06
     gö
    -0.06
     Kurds
    -0.06
    ",
↵
    -0.06
    .todos
    -0.06
    Fred
    -0.06
    POSITIVE LOGITS
    orative
    0.06
     eliminating
    0.06
     allocating
    0.06
     compliance
    0.06
     Fuji
    0.06
    orgt
    0.06
     asks
    0.06
     Copp
    0.06
    grunt
    0.06
    543
    0.06
    Activations Density 0.005%

    No Known Activations