Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 91570
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (integers or floating‐point numbers) in code.

    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
    中國
    -0.07
    ीटर
    -0.06
     airline
    -0.06
    @Slf
    -0.06
     compute
    -0.06
     resist
    -0.06
     music
    -0.06
    士
    -0.06
     meter
    -0.06
     invading
    -0.06
    POSITIVE LOGITS
     passé
    0.07
    ΙΑΣ
    0.07
     себ
    0.06
    ための
    0.06
     BrowserAnimationsModule
    0.06
    ’yi
    0.06
    >About
    0.06
    .SECONDS
    0.06
     �
    0.06
     روی
    0.06
    Activations Density 0.024%

    No Known Activations