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. 81438
    Prev
    Next
    INDEX
    Explanations

    Numbers and statistics

    np_max-act · gemini-2.0-flash

    The neuron is strongly triggered by numeric tokens—digits, counts, and quantities—highlighting when the text contains numbers.

    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
    节点
    -0.07
    ogram
    -0.07
     Pe
    -0.06
     gaussian
    -0.06
    -bed
    -0.06
     популяр
    -0.06
     Gram
    -0.06
    231
    -0.06
     �
    -0.06
     pizza
    -0.06
    POSITIVE LOGITS
     ;-
    0.07
    @NgModule
    0.06
     *,
    0.06
    =*/
    0.06
    izia
    0.06
     黄
    0.06
    SCRIPTOR
    0.06
     індив
    0.06
     '='
    0.06
     (:
    0.06
    Activations Density 0.039%

    No Known Activations