© 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. 14002
    Prev
    Next
    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    The neuron fires on discourse markers and intensifying adverbs—words like really, actually, sort of, and other hedges that add emphasis or qualification.

    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
     Tibetan
    -0.06
    texts
    -0.06
    职
    -0.06
     Polymer
    -0.06
     Kris
    -0.06
     symmetry
    -0.06
     Gain
    -0.06
    tribution
    -0.06
    ไร
    -0.06
     Pose
    -0.05
    POSITIVE LOGITS
     był
    0.07
    ด
    0.06
    \Validation
    0.06
     amo
    0.06
     теат
    0.06
    neo
    0.06
     wonderful
    0.06
    _substr
    0.06
    орг
    0.06
     สามารถ
    0.06
    Activations Density 0.126%

    No Known Activations