© 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. 46959
    Prev
    Next
    INDEX
    Explanations

    flash

    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
     Daniel
    -0.07
     build
    -0.07
     Matthew
    -0.07
    .Pod
    -0.07
     finds
    -0.07
    Miller
    -0.06
     Gordon
    -0.06
     Serv
    -0.06
     FIND
    -0.06
     yönetic
    -0.06
    POSITIVE LOGITS
     KeyError
    0.07
     весь
    0.07
     ***/↵
    0.07
     дор
    0.06
    _VOICE
    0.06
     gritty
    0.06
    WithValue
    0.06
     reckon
    0.06
    ToDate
    0.06
    [MAXN
    0.06
    Activations Density 0.004%

    No Known Activations