© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91929
    Prev
    Next
    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash

    This neuron detects the “?” nullable-type marker in Kotlin type declarations.

    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
     PCR
    -0.06
    _grid
    -0.06
     replied
    -0.06
    -repeat
    -0.06
     agrees
    -0.06
    .gray
    -0.06
    Used
    -0.06
    TOOLS
    -0.06
    .rx
    -0.06
     รวม
    -0.06
    POSITIVE LOGITS
     heightened
    0.07
     червня
    0.07
     организации
    0.06
    ΑΠ
    0.06
     офици
    0.06
    //#
    0.06
    按
    0.06
    無し�
    0.06
    ，一
    0.06
    :nth
    0.06
    Activations Density 0.004%

    No Known Activations