© 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. 44502
    Prev
    Next
    INDEX
    Explanations

    immobil

    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
    Not in Any Lists

    No Comments

    Negative Logits
     entertained
    -0.07
     breaker
    -0.07
     ipad
    -0.06
     scraper
    -0.06
     ws
    -0.06
    Hex
    -0.06
    ΟΝ
    -0.06
    Marks
    -0.06
     Viking
    -0.06
    ον
    -0.06
    POSITIVE LOGITS
     immobil
    0.11
    ทางการ
    0.06
    rientation
    0.06
    mey
    0.06
     plural
    0.06
    .eth
    0.06
    .bootstrapcdn
    0.06
    dığını
    0.06
    heel
    0.06
    roomId
    0.06
    Activations Density 0.002%

    No Known Activations