© 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. 11-RESID-POST-AA
    11. 101088
    Prev
    Next
    INDEX
    Explanations

    class

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Warm
    -0.08
     deltas
    -0.07
    recall
    -0.07
     Preference
    -0.07
     Sinh
    -0.06
     websocket
    -0.06
    _features
    -0.06
     Mam
    -0.06
    embed
    -0.06
     男
    -0.06
    POSITIVE LOGITS
     strs
    0.07
    .cgColor
    0.07
     깨
    0.07
    ipsis
    0.07
    ainties
    0.06
     treeNode
    0.06
     NSError
    0.06
    .DotNetBar
    0.06
    TypeInfo
    0.06
     Settlement
    0.06
    Activations Density 0.028%

    No Known Activations