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. 130589
    Prev
    Next
    INDEX
    Explanations

    /docs

    np_max-act · gemini-2.0-flash

    The neuron detects references to MDN (developer.mozilla.org) documentation URLs.

    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
    ICC
    -0.07
    ячи
    -0.07
    jpeg
    -0.06
     ấm
    -0.06
    Updating
    -0.06
    ahtar
    -0.06
    ír
    -0.06
    -word
    -0.06
    рев
    -0.06
    JECTION
    -0.06
    POSITIVE LOGITS
    碰
    0.07
    /k
    0.07
    ucceed
    0.06
     taxed
    0.06
    со
    0.06
    .’”↵↵
    0.06
     после
    0.06
     Thurs
    0.06
    ์,
    0.06
     Delaware
    0.06
    Activations Density 0.000%

    No Known Activations