© 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. 11-RESID-POST-AA
    11. 102102
    Prev
    Next
    INDEX
    Explanations

    categories

    np_max-act · gemini-2.0-flash

    names of British politicians and their associated details.

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

    The neuron specializes in spotting numeric year tokens (and connecting hyphens) in date ranges—e.g. the birth–death years in metadata/category lines.

    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
     Hak
    -0.07
     پرد
    -0.07
    -parse
    -0.06
    _rect
    -0.06
     "@
    -0.06
     municip
    -0.06
    maxLength
    -0.06
    _reward
    -0.06
    631
    -0.06
     repeat
    -0.06
    POSITIVE LOGITS
    の子
    0.07
    Obsolete
    0.07
    Called
    0.06
    .argument
    0.06
    //{↵
    0.06
    macı
    0.06
    .files
    0.06
    вид
    0.06
     amour
    0.06
    digital
    0.06
    Activations Density 0.003%

    No Known Activations