© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 34806
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    Dates in ISO-like numeric format (YYYY-MM-DD).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .gms
    -0.07
     Weinstein
    -0.07
     Tre
    -0.07
     Porto
    -0.07
     PowerShell
    -0.07
     causing
    -0.07
     Manit
    -0.06
     arreglo
    -0.06
    isory
    -0.06
    abling
    -0.06
    POSITIVE LOGITS
     mirror
    0.07
    holder
    0.06
    fadeIn
    0.06
    чна
    0.06
     slopes
    0.06
    lambda
    0.06
    remarks
    0.06
    .columns
    0.06
    _upper
    0.06
    Marks
    0.06
    Activations Density 0.006%

    No Known Activations