© 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. 36576
    Prev
    Next
    INDEX
    Explanations

    graft

    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
    (Time
    -0.07
     thunder
    -0.07
    ideon
    -0.06
    \Field
    -0.06
    ZE
    -0.06
     sana
    -0.06
    ahrungen
    -0.06
    ież
    -0.06
    backend
    -0.06
     tabs
    -0.06
    POSITIVE LOGITS
     graft
    0.08
    -plus
    0.07
    gf
    0.07
     Weird
    0.06
     cours
    0.06
    Naming
    0.06
    -h
    0.06
    	expected
    0.06
     breaches
    0.06
     gimm
    0.06
    Activations Density 0.002%

    No Known Activations