© 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. 8983
    Prev
    Next
    INDEX
    Explanations

    isease

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting the word “disease” (and its plural form “diseases”).

    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
     repr
    -0.07
     PPP
    -0.07
     utterly
    -0.07
    ropped
    -0.07
     chairs
    -0.07
     Ratio
    -0.07
     awkward
    -0.07
     Arr
    -0.07
     Corner
    -0.07
    Lit
    -0.07
    POSITIVE LOGITS
     disease
    0.15
     Disease
    0.14
     diseases
    0.11
     Diseases
    0.09
    _solve
    0.08
     Dise
    0.08
    	game
    0.07
    (data
    0.07
     dise
    0.07
     Diane
    0.07
    Activations Density 0.023%

    No Known Activations