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. 130475
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron responds to numerical tokens (especially decimal numbers) 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
    -d
    -0.06
     );
    ↵
    ↵
    -0.06
    ोध
    -0.06
     مهم
    -0.06
    há
    -0.06
    -wife
    -0.06
    -r
    -0.06
    ,exports
    -0.05
    _HELPER
    -0.05
     sar
    -0.05
    POSITIVE LOGITS
     textual
    0.07
    	strcpy
    0.07
    alen
    0.07
    ‐‐
    0.07
    [url
    0.07
    .GetData
    0.06
    elf
    0.06
     उसस
    0.06
     بات
    0.06
     sàng
    0.06
    Activations Density 0.174%

    No Known Activations