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. 86343
    Prev
    Next
    INDEX
    Explanations

    L

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—especially decimal numbers and statistics.

    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
    antu
    -0.07
    ,看
    -0.06
    ิสต
    -0.06
    immer
    -0.06
    =username
    -0.06
     nerv
    -0.06
    !;↵
    -0.06
    okud
    -0.06
     kijken
    -0.06
     qualified
    -0.06
    POSITIVE LOGITS
     İmpar
    0.07
    ButtonType
    0.07
    >G
    0.07
    евой
    0.06
    _DROP
    0.06
     uygulan
    0.06
    <W
    0.06
     trg
    0.06
     eros
    0.06
     Boo
    0.06
    Activations Density 0.076%

    No Known Activations