© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55483
    Prev
    Next
    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurement values (especially decimal numbers and statistics) in the 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
    companies
    -0.06
     Decision
    -0.06
    	last
    -0.06
    %A
    -0.06
     Completely
    -0.06
     Licensed
    -0.06
    _rows
    -0.06
     From
    -0.06
     Ten
    -0.06
    egan
    -0.06
    POSITIVE LOGITS
     buộc
    0.06
     Ελλάδα
    0.06
     olab
    0.06
     прежде
    0.06
    layarak
    0.06
    _align
    0.06
     nije
    0.06
     immer
    0.06
    잡담
    0.06
    bere
    0.06
    Activations Density 0.012%

    No Known Activations