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. 86000
    Prev
    Next
    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash

    The neuron is specialized to spot floating‐point numeric values (decimal numbers) embedded in HTML or CSS attribute strings.

    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
    丽
    -0.06
    categories
    -0.06
     offices
    -0.06
     Sample
    -0.06
     conscient
    -0.06
     contour
    -0.06
    Accessibility
    -0.05
     olası
    -0.05
    companies
    -0.05
     Throw
    -0.05
    POSITIVE LOGITS
     مرة
    0.06
    CMD
    0.06
    _tar
    0.06
    Img
    0.06
    :CGPoint
    0.06
     :
    ↵
    0.06
    _TMP
    0.06
     gangs
    0.06
    _ERR
    0.06
    =[]
    0.06
    Activations Density 0.016%

    No Known Activations