© 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. 91989
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—especially floating‐point literals—embedded in code.

    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
     weekends
    -0.06
    -spec
    -0.06
    ')->__('
    -0.06
    .y
    -0.06
     Killed
    -0.06
    135
    -0.06
    няют
    -0.06
    -Benz
    -0.06
    .active
    -0.06
    _sl
    -0.06
    POSITIVE LOGITS
     nội
    0.07
     CRUD
    0.07
    Conversation
    0.07
    	global
    0.06
    >
    0.06
    nice
    0.06
     otáz
    0.06
    .transforms
    0.06
    ture
    0.06
     worn
    0.06
    Activations Density 0.355%

    No Known Activations