© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 84098
    Prev
    Next
    INDEX
    Explanations

    of

    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
     wir
    -0.06
    bu
    -0.06
    fax
    -0.06
     gör
    -0.06
     Aus
    -0.06
    _accuracy
    -0.06
     bookmark
    -0.06
    owered
    -0.06
    BU
    -0.06
     disturb
    -0.06
    POSITIVE LOGITS
    sport
    0.07
     REST
    0.07
    крет
    0.06
     YE
    0.06
    adget
    0.06
     свидетель
    0.06
     　　　　
    0.06
    يتي
    0.06
    PostalCodes
    0.06
    ewhere
    0.06
    Activations Density 0.000%

    No Known Activations