© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125937
    Prev
    Next
    INDEX
    Explanations

    deformation

    np_max-act · gemini-2.0-flash

    The neuron responds to descriptions of mechanical deformation or elastic stress (e.g. “elastic,” “deformation,” “impairs”) within technical patent text.

    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
     учнів
    -0.07
    talya
    -0.07
    _derivative
    -0.07
     Kho
    -0.07
    .putString
    -0.06
    Technical
    -0.06
    .Copy
    -0.06
    Ng
    -0.06
    ていた
    -0.06
    nestjs
    -0.06
    POSITIVE LOGITS
    DOM
    0.06
     listings
    0.06
    --+
    0.06
    (times
    0.06
    (Level
    0.06
    дер
    0.06
     line
    0.06
    cing
    0.06
    mens
    0.06
     LINE
    0.06
    Activations Density 0.016%

    No Known Activations