© 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. 27-RESID-POST-AA
    11. 7060
    Prev
    Next
    INDEX
    Explanations

    longitudinal studies and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kuwait
    -0.08
     الو
    -0.07
    نة
    -0.07
     Gun
    -0.06
    먼
    -0.06
     bank
    -0.06
     vibe
    -0.06
     Roots
    -0.06
    .shapes
    -0.06
    leanor
    -0.06
    POSITIVE LOGITS
    (artist
    0.07
    ');"
    0.07
    En
    0.07
    INC
    0.06
     Compet
    0.06
     hostage
    0.06
    icc
    0.06
     obstruct
    0.06
     endIndex
    0.06
     gathered
    0.06
    Activations Density 0.026%

    No Known Activations