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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119735
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    instances of dialogue or Q&A structure, such as speaker attributions, interview labels with colons, and question/response phrasing.

    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
     ساعت
    -0.07
     Î
    -0.07
    Twig
    -0.07
     rund
    -0.06
    _UID
    -0.06
     Planned
    -0.06
    _ub
    -0.06
    _auto
    -0.06
    hlen
    -0.06
    ><?=
    -0.06
    POSITIVE LOGITS
     packet
    0.06
    ordum
    0.06
    Blockchain
    0.06
    ड़क
    0.06
    air
    0.06
    ongoose
    0.06
    urons
    0.06
     Insert
    0.06
    ervo
    0.06
     credited
    0.06
    Activations Density 0.276%

    No Known Activations