© 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. 73670
    Prev
    Next
    INDEX
    Explanations

    nervousness and anxiety

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of managing nerves or anxiety (e.g., “nerves,” “under control,” “during”).

    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
     숙
    -0.07
     prefers
    -0.06
    _controller
    -0.06
    DataContext
    -0.06
    Metric
    -0.06
    Freq
    -0.06
    (percent
    -0.06
     kwargs
    -0.06
    (exec
    -0.05
    decltype
    -0.05
    POSITIVE LOGITS
    SYM
    0.07
     той
    0.06
    _spell
    0.06
    Loan
    0.06
     glare
    0.06
     taxation
    0.06
     empire
    0.06
     similarly
    0.06
    >v
    0.06
    (/^\
    0.06
    Activations Density 0.046%

    No Known Activations