© 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. 15-RESID-POST-AA
    11. 87972
    Prev
    Next
    INDEX
    Explanations

    Reported events/statistics

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -processing
    -0.07
     defense
    -0.07
     Tul
    -0.06
    _Code
    -0.06
     wearing
    -0.06
     sleeping
    -0.06
     Missile
    -0.06
     forfeiture
    -0.06
     repayment
    -0.06
     Couple
    -0.06
    POSITIVE LOGITS
    ALSE
    0.07
    %=
    0.07
    	HX
    0.07
    (*)(
    0.06
     chết
    0.06
    .getHours
    0.06
    .ajax
    0.06
    _abort
    0.06
    -ajax
    0.06
     quyết
    0.06
    Activations Density 0.042%

    No Known Activations