© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128425
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash

    This neuron detects hedging or evidential cue words that qualify statements (e.g. “likely,” “possible,” “evidence,” “surprise,” “suggest”).

    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
    Offsets
    -0.06
     bored
    -0.06
    资产
    -0.06
     grievances
    -0.06
     highlight
    -0.06
    jandro
    -0.06
    inci
    -0.06
    (player
    -0.06
     ζ
    -0.06
    OTES
    -0.06
    POSITIVE LOGITS
    COVER
    0.08
     elementType
    0.06
     คน
    0.06
     другим
    0.06
     порядку
    0.06
     peaceful
    0.06
     bridal
    0.06
     bows
    0.06
    (--
    0.06
     nous
    0.06
    Activations Density 0.155%

    No Known Activations