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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 73771
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron activates on language describing a physical contest—particularly arm-wrestling–style actions (pushing, pulling, striving to gain the upper hand).

    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
     sui
    -0.08
    _perf
    -0.06
    114
    -0.06
    timestamps
    -0.06
    _PARAM
    -0.06
     Curry
    -0.06
     zoning
    -0.06
     rapid
    -0.06
    854
    -0.06
    Width
    -0.06
    POSITIVE LOGITS
    ΗΝ
    0.07
    úp
    0.07
     notre
    0.06
     kriz
    0.06
    �다
    0.06
     Теп
    0.06
     jmp
    0.06
    ektedir
    0.06
    τηκε
    0.06
     π
    0.06
    Activations Density 0.044%

    No Known Activations