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. 86248
    Prev
    Next
    INDEX
    Explanations

    scientific data

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric values (numbers with a decimal point) 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
     issues
    -0.07
     Manitoba
    -0.06
    ुख
    -0.06
     свя
    -0.06
    DIST
    -0.06
    .Retrofit
    -0.06
     distributed
    -0.06
     Demonstr
    -0.06
    くん
    -0.06
    Soup
    -0.06
    POSITIVE LOGITS
    (=
    0.07
    眠
    0.07
    ollider
    0.06
    omers
    0.06
    тура
    0.06
    ...");↵↵
    0.06
     experimented
    0.06
    rightness
    0.06
     ke
    0.06
     psychology
    0.06
    Activations Density 0.000%

    No Known Activations