Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130231
    Prev
    Next
    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash

    This neuron detects date references, particularly month names and day‐and‐year numbers in court document headings and orders.

    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
     Auxiliary
    -0.07
    esin
    -0.07
     trained
    -0.06
    //-----------------------------------------------------------------------------↵
    -0.06
     Ronaldo
    -0.06
    !=
    -0.06
     Glover
    -0.06
    /fw
    -0.06
     eg
    -0.06
     Lond
    -0.06
    POSITIVE LOGITS
    _host
    0.07
    atorio
    0.06
    ,SIGNAL
    0.06
     bilgi
    0.06
    (SQLException
    0.06
     평균
    0.06
     περ
    0.06
    (Yii
    0.06
     voir
    0.06
    .Mongo
    0.06
    Activations Density 0.006%

    No Known Activations