© 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 EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 65206
    Prev
    Next
    INDEX
    Explanations

    ness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    르고
    -0.07
    ีอ
    -0.06
     simplicity
    -0.06
    _BLK
    -0.06
    rg
    -0.06
    最近
    -0.06
     guilt
    -0.06
    →
    -0.06
    _merged
    -0.06
     підпис
    -0.06
    POSITIVE LOGITS
    becca
    0.07
     "<<
    0.07
     NavController
    0.07
    CREASE
    0.06
     контроль
    0.06
     cread
    0.06
     css
    0.06
     Drawable
    0.06
     useHistory
    0.06
     do
    0.06
    Activations Density 0.003%

    No Known Activations