© 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. 126003
    Prev
    Next
    INDEX
    Explanations

    Blurriness

    np_max-act · gemini-2.0-flash

    The neuron responds to words evoking haze, blur, or fog—terms that describe an unclear, misty, or murky state.

    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
    _invoke
    -0.07
     Saul
    -0.07
     reb
    -0.07
    偷
    -0.07
    -flow
    -0.07
    _LP
    -0.07
    -response
    -0.06
    @testable
    -0.06
     needed
    -0.06
    _PO
    -0.06
    POSITIVE LOGITS
     blur
    0.09
     obscured
    0.07
     blurry
    0.07
    urring
    0.07
     Blur
    0.07
     obscure
    0.07
     opaque
    0.07
     govern
    0.07
    ajan
    0.07
     murky
    0.07
    Activations Density 0.018%

    No Known Activations