© 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. 11-RESID-POST-AA
    11. 68519
    Prev
    Next
    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash

    people in the film and music industry with notable achievements or roles.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron identifies mentions of a person’s professional role or occupation (e.g. director, cinematographer, producer).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zug
    -0.07
     FormControl
    -0.06
    ppe
    -0.06
    .SimpleButton
    -0.06
     оказ
    -0.06
    .getTitle
    -0.06
    ItemImage
    -0.06
    ffset
    -0.06
    ToFront
    -0.06
     HDR
    -0.06
    POSITIVE LOGITS
     rib
    0.06
     不
    0.06
    .son
    0.06
    hello
    0.06
     GB
    0.06
    )|(
    0.06
    Fra
    0.06
    buster
    0.06
    _ask
    0.06
    ILITIES
    0.06
    Activations Density 0.034%

    No Known Activations