© 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. 75006
    Prev
    Next
    INDEX
    Explanations

    Computer power supplies

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of power usage—especially tokens like “power,” “power consumption,” and “power supply.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical specifications and details related to computer components.

    oai_token-act-pair · gpt-4o-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
    Appointment
    -0.07
     blas
    -0.07
    egration
    -0.06
    .ai
    -0.06
    .array
    -0.06
    評
    -0.06
     Seahawks
    -0.06
     olacak
    -0.06
    ΜΑ
    -0.06
    TeV
    -0.06
    POSITIVE LOGITS
     capitalist
    0.07
     EQUI
    0.07
    ()%
    0.07
    monton
    0.07
     yeast
    0.06
     boss
    0.06
    (tr
    0.06
    _INTEGER
    0.06
     mutex
    0.06
     almonds
    0.06
    Activations Density 0.006%

    No Known Activations