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. 81430
    Prev
    Next
    INDEX
    Explanations

    Quantities and amounts

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens and list‐ or section‐enumeration markers (i.e. numbers and numbered labels in the text).

    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
    .quick
    -0.07
     CGAffineTransform
    -0.07
    igital
    -0.07
    .games
    -0.06
    .Alpha
    -0.06
     Cross
    -0.06
    春
    -0.06
     πρώ
    -0.06
    夜
    -0.06
     motorcycles
    -0.06
    POSITIVE LOGITS
    (jButton
    0.06
     الجن
    0.06
    (IDC
    0.06
     slou
    0.06
    くと
    0.06
     tad
    0.06
     Seks
    0.06
    REET
    0.06
     clearColor
    0.06
    gresql
    0.06
    Activations Density 0.082%

    No Known Activations