© 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. 23-RESID-POST-AA
    11. 68993
    Prev
    Next
    INDEX
    Explanations

    Business and technology context

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    780
    -0.07
    하세요
    -0.07
     surpassed
    -0.06
    лению
    -0.06
    .accuracy
    -0.06
    NIEnv
    -0.06
    بان
    -0.06
     parked
    -0.06
     COURT
    -0.06
     cultiv
    -0.06
    POSITIVE LOGITS
     ACS
    0.07
     ssl
    0.06
    ]=='
    0.06
    (as
    0.06
    ,:
    0.06
    atis
    0.06
     freshmen
    0.06
     Ιω
    0.06
     ăn
    0.06
    orian
    0.06
    Activations Density 0.054%

    No Known Activations