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. 130392
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numeric tokens (e.g. floating-point values, p-values, percentages) 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
    本当に
    -0.07
    едак
    -0.06
     teachers
    -0.06
    Calls
    -0.06
     曰
    -0.06
    /";↵↵
    -0.06
    inburgh
    -0.06
     яр
    -0.06
    );
    
    ↵
    -0.06
    ire
    -0.06
    POSITIVE LOGITS
     Cop
    0.07
    elligence
    0.07
    Activities
    0.06
     Corona
    0.06
     SENSOR
    0.06
     Origin
    0.06
     NotFound
    0.06
    IGENCE
    0.06
     cou
    0.06
     poem
    0.06
    Activations Density 0.099%

    No Known Activations