© 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. 114617
    Prev
    Next
    INDEX
    Explanations

    gg

    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
     SINGLE
    -0.06
     Fot
    -0.06
     squadron
    -0.06
     Saf
    -0.06
    ifth
    -0.06
     Kent
    -0.06
    haf
    -0.06
    reward
    -0.06
     Kumar
    -0.06
     traumat
    -0.06
    POSITIVE LOGITS
     で
    0.08
    CppMethod
    0.07
     yacc
    0.07
    )((((
    0.07
    Ger
    0.07
     nước
    0.07
     تمر
    0.07
    _flash
    0.07
    (substr
    0.07
    aring
    0.07
    Activations Density 0.002%

    No Known Activations