© 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. 124862
    Prev
    Next
    INDEX
    Explanations

    guess

    np_max-act · gemini-2.0-flash

    This neuron detects hedging or speaker-opinion phrases (e.g. “I think,” “I guess,” “I suppose”).

    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
    _remaining
    -0.07
    bounded
    -0.07
    руч
    -0.06
     кад
    -0.06
    apixel
    -0.06
    ampling
    -0.06
    ců
    -0.06
    jej
    -0.06
    th
    -0.06
     contender
    -0.06
    POSITIVE LOGITS
     labore
    0.08
    (())↵
    0.08
     серпня
    0.07
     uLocal
    0.07
     Cement
    0.07
     stellt
    0.06
     탈
    0.06
    (cancel
    0.06
     臺
    0.06
     тяжел
    0.06
    Activations Density 0.013%

    No Known Activations