Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84381
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens representing decimal numbers (floating‐point literals).

    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
     Unsure
    -0.06
     instant
    -0.06
    ütün
    -0.06
    used
    -0.06
     toned
    -0.06
     Pune
    -0.06
    edic
    -0.06
     mastering
    -0.06
    _verification
    -0.06
     proceed
    -0.06
    POSITIVE LOGITS
    _kses
    0.07
    Manufact
    0.07
     dernier
    0.06
    Boot
    0.06
     ileri
    0.06
     bulunmaktadır
    0.06
    371
    0.06
    wheel
    0.06
    大き
    0.06
     ges
    0.06
    Activations Density 0.027%

    No Known Activations