© 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. 24601
    Prev
    Next
    INDEX
    Explanations

    that

    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
    Negative Logits
    だって
    -0.06
    화를
    -0.06
     lone
    -0.06
     brainstorm
    -0.06
    _clause
    -0.06
    Saudi
    -0.06
    conditions
    -0.06
    alink
    -0.06
     referencia
    -0.06
    世
    -0.06
    POSITIVE LOGITS
     trailed
    0.07
     입니다
    0.06
     ©
    0.06
     pellets
    0.06
     imperfect
    0.06
    Jets
    0.06
     '''↵↵
    0.06
     Late
    0.06
     negot
    0.06
    овали
    0.06
    Activations Density 0.072%

    No Known Activations