© 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. 15-RESID-POST-AA
    11. 24295
    Prev
    Next
    INDEX
    Explanations

    articles

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andır
    -0.07
    chas
    -0.07
     @{@"
    -0.06
    .Click
    -0.06
     JNI
    -0.06
     SEXP
    -0.06
    GetValue
    -0.06
     Lists
    -0.06
    oğu
    -0.06
     cref
    -0.06
    POSITIVE LOGITS
     specifies
    0.07
    +f
    0.06
     ladies
    0.06
     maintain
    0.06
    [$
    0.06
     харч
    0.06
     aggreg
    0.06
    ！」
    0.06
    406
    0.06
    EAR
    0.06
    Activations Density 0.023%

    No Known Activations