© 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. 63756
    Prev
    Next
    INDEX
    Explanations

    computer software/websites

    np_max-act · gemini-2.0-flash

    markers denoting the assistant’s role/turn in chat-style header metadata.

    oai_token-act-pair · gpt-5Triggered 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
    [,
    -0.06
     meinen
    -0.06
     П
    -0.06
     Maryland
    -0.06
     sabe
    -0.06
     самых
    -0.06
     ten
    -0.06
     bordered
    -0.06
    .Build
    -0.06
    Win
    -0.06
    POSITIVE LOGITS
    _quest
    0.07
    >()->
    0.07
    _<?
    0.07
    estureRecognizer
    0.07
    .baseUrl
    0.06
    롯
    0.06
    okemon
    0.06
    .clientHeight
    0.06
    .boost
    0.06
     scholar
    0.06
    Activations Density 0.045%

    No Known Activations