© 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. 7-RESID-POST-AA
    11. 45354
    Prev
    Next
    INDEX
    Explanations

    nitro compounds

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     curse
    -0.07
     ledger
    -0.06
    checkbox
    -0.06
    ická
    -0.06
    _filt
    -0.06
     cautioned
    -0.06
     lamin
    -0.06
    xCB
    -0.06
    Alive
    -0.06
    ObjectId
    -0.06
    POSITIVE LOGITS
    <|begin_of_text|>
    0.07
     слу
    0.06
    描
    0.06
     어
    0.06
    profit
    0.06
     //↵
    0.06
    )，
    0.06
    	dfs
    0.06
     WW
    0.06
    scanner
    0.06
    Activations Density 0.002%

    No Known Activations