© 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. 23-RESID-POST-AA
    11. 63018
    Prev
    Next
    INDEX
    Explanations

    tips, tricks, strategies

    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
    Negative Logits
    target
    -0.07
     temperatura
    -0.07
    svc
    -0.06
    Consider
    -0.06
    OMATIC
    -0.06
     >(
    -0.06
    Technical
    -0.06
     target
    -0.06
    048
    -0.06
    ная
    -0.06
    POSITIVE LOGITS
    ::::::::::::::::::::::::::::::::
    0.08
     getWidth
    0.07
    _render
    0.06
    .columnHeader
    0.06
     incontr
    0.06
    meet
    0.06
    ี
    0.06
    611
    0.06
     Discrim
    0.06
     CHUNK
    0.06
    Activations Density 0.059%

    No Known Activations