© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 85737
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on Objective-C compiler and API annotation macros (e.g. NS_AVAILABLE, NS_UNAVAILABLE, NS_DESIGNATED_INITIALIZER, API_AVAILABLE, FOUNDATION_EXPORT, NS_ASSUME_NONNULL, etc.).

    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
    (".",
    -0.07
    oo
    -0.07
    iv
    -0.07
    IES
    -0.07
    enou
    -0.07
    uni
    -0.06
    Unknown
    -0.06
    endant
    -0.06
     يو
    -0.06
    member
    -0.06
    POSITIVE LOGITS
     důvodu
    0.07
     Adolf
    0.07
     Nigel
    0.07
     degraded
    0.07
     magg
    0.07
    `t
    0.06
    $errors
    0.06
     všech
    0.06
     περισσότε
    0.06
    bugs
    0.06
    Activations Density 0.153%

    No Known Activations