© 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. 37717
    Prev
    Next
    INDEX
    Explanations

    Dim

    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
    ैं।↵↵
    -0.07
     prat
    -0.07
     barring
    -0.07
    supply
    -0.06
    .setOn
    -0.06
     Мет
    -0.06
     relatively
    -0.06
    >>&
    -0.06
     groove
    -0.06
    @
    -0.06
    POSITIVE LOGITS
     Generate
    0.08
     nghĩa
    0.08
     employs
    0.07
    ING
    0.06
    โล
    0.06
    rightness
    0.06
    phere
    0.06
    .hom
    0.06
    addClass
    0.06
     PIN
    0.06
    Activations Density 0.030%

    No Known Activations