© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110434
    Prev
    Next
    INDEX
    Explanations

    fighting

    np_max-act · gemini-2.0-flash

    The neuron pulses on terms that describe combat moves or striking actions (e.g. punch, kick, jab, throwing, landing, counters) in a fight context.

    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
     userType
    -0.07
     gays
    -0.07
    ктив
    -0.07
     مرتبط
    -0.06
    	ev
    -0.06
    modes
    -0.06
     Menschen
    -0.06
    ujeme
    -0.06
    _games
    -0.06
    HOOK
    -0.06
    POSITIVE LOGITS
    姓
    0.07
    (begin
    0.07
     đâu
    0.06
    scaling
    0.06
     stra
    0.06
     Hubbard
    0.06
     stamina
    0.06
     +#
    0.06
     सम
    0.06
    _Grid
    0.06
    Activations Density 0.006%

    No Known Activations