© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    initialize

    np_max-act · gemini-2.0-flash

    This neuron detects C/C++ brace‐enclosed initializer lists (e.g. the “= { … }” syntax).

    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
     νό
    -0.07
    .write
    -0.06
     링크
    -0.06
    ollection
    -0.06
    /tags
    -0.06
    .SOCK
    -0.06
     vš
    -0.06
     бізнес
    -0.06
     WaitForSeconds
    -0.06
     gyro
    -0.05
    POSITIVE LOGITS
    家族
    0.07
    .'↵
    0.07
    _remote
    0.06
     IMPORTANT
    0.06
    izzling
    0.06
    _again
    0.06
    /services
    0.06
     QUICK
    0.06
    Initializer
    0.06
    콘
    0.06
    Activations Density 0.006%

    No Known Activations