© 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. 68791
    Prev
    Next
    INDEX
    Explanations

    say "out"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     comprise
    -0.07
    ительный
    -0.07
    .lwjgl
    -0.06
     distancing
    -0.06
     decreasing
    -0.06
    ди
    -0.06
     communicates
    -0.06
    omed
    -0.06
     techno
    -0.06
    993
    -0.06
    POSITIVE LOGITS
    _mod
    0.06
     repairs
    0.06
    ětí
    0.06
     ];↵↵
    0.06
     inputData
    0.06
    �
    0.06
    ]|[
    0.06
    ництва
    0.06
    0.06
     CONST
    0.06
    Activations Density 0.007%

    No Known Activations