© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126772
    Prev
    Next
    INDEX
    Explanations

    uncertain

    np_max-act · gemini-2.0-flash

    This neuron activates on words expressing uncertainty or unpredictability (e.g., “uncertain,” “uncertainty,” “unpredictable”).

    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
    445
    -0.07
     Loy
    -0.07
    vou
    -0.07
     вор
    -0.07
    "display
    -0.07
    296
    -0.06
     Loves
    -0.06
     بإ
    -0.06
    Shown
    -0.06
    appName
    -0.06
    POSITIVE LOGITS
     uncertainty
    0.13
     uncertain
    0.11
     uncertainties
    0.10
     cy
    0.08
     tomorrow
    0.07
    ypical
    0.07
     uncert
    0.07
    urray
    0.07
     doubt
    0.07
    erty
    0.07
    Activations Density 0.009%

    No Known Activations