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

    Neuronpedia

    Jacobian LensNEW
    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. 38924
    Prev
    Next
    INDEX
    Explanations

    Technical writing/problem descriptions

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on technical descriptive terms and discourse connectors (e.g. “resulting,” “thus,” “circular,” “metal,” “parts,” “costs”) typical of formal engineering or patent-style explanations.

    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
    गर
    -0.07
     book
    -0.07
     Principle
    -0.06
    inciple
    -0.06
    -photo
    -0.06
    닝
    -0.06
    868
    -0.06
     Diversity
    -0.06
     searchable
    -0.06
    ูน
    -0.06
    POSITIVE LOGITS
    .didReceiveMemoryWarning
    0.07
     FEATURE
    0.07
    สถ
    0.07
     vẻ
    0.06
     Üç
    0.06
    crafted
    0.06
    Alan
    0.06
    024
    0.06
     أمريكي
    0.06
     ResourceBundle
    0.06
    Activations Density 0.050%

    No Known Activations