© 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. 98809
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    the presence of numeric tokens (numerals, years, decimals, and other number-like strings).

    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
    っぱい
    -0.07
    領
    -0.07
    antom
    -0.07
    丸
    -0.06
     son
    -0.06
    ernel
    -0.06
     kapsamında
    -0.06
    azines
    -0.06
    -Benz
    -0.06
    ipped
    -0.06
    POSITIVE LOGITS
     unnecessary
    0.06
     closed
    0.06
     regard
    0.06
    .getParameter
    0.06
    .Types
    0.06
     فهم
    0.06
     Posted
    0.06
     Sala
    0.06
     Aub
    0.06
     lighter
    0.06
    Activations Density 0.320%

    No Known Activations