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. 40407
    Prev
    Next
    INDEX
    Explanations

    ocoa

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “Cocoa” (especially “Cocoa Touch”) framework identifiers in XML files.

    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
     الان
    -0.07
     myth
    -0.07
     myths
    -0.06
    πουργ
    -0.06
    Device
    -0.06
     Ireland
    -0.06
     Paint
    -0.06
    .getP
    -0.06
    _exp
    -0.06
     외국
    -0.06
    POSITIVE LOGITS
    TabIndex
    0.06
     gg
    0.06
     ))}↵
    0.06
    =k
    0.06
     tomorrow
    0.06
    ogy
    0.06
     Dissertation
    0.06
    отов
    0.06
     ка
    0.06
    '])?
    0.06
    Activations Density 0.000%

    No Known Activations