© 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. 41363
    Prev
    Next
    INDEX
    Explanations

    torque

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the term “torque,” particularly where it quantifies or discusses torque values in technical contexts.

    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
    vid
    -0.07
     digits
    -0.07
     admitted
    -0.07
    егист
    -0.07
     dried
    -0.06
     ostrov
    -0.06
    free
    -0.06
     hastily
    -0.06
    یت
    -0.06
    enen
    -0.06
    POSITIVE LOGITS
     torque
    0.15
     Enrique
    0.08
    <Q
    0.07
     Serge
    0.07
     doz
    0.07
    ButtonClick
    0.07
     setTime
    0.07
    (Mouse
    0.07
     Tape
    0.06
     옥
    0.06
    Activations Density 0.002%

    No Known Activations