© 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. 6398
    Prev
    Next
    INDEX
    Explanations

    def

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) 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
     ||
    -0.07
    �
    -0.07
    Yet
    -0.06
     majestic
    -0.06
    .eulerAngles
    -0.06
    Rel
    -0.06
    blr
    -0.06
    .bad
    -0.06
     Vanilla
    -0.06
     boots
    -0.06
    POSITIVE LOGITS
    picture
    0.07
     Fla
    0.07
    تبه
    0.06
     McD
    0.06
    غة
    0.06
     özellik
    0.06
     PROGMEM
    0.06
     δι
    0.06
    OLEAN
    0.06
    ()='
    0.06
    Activations Density 0.012%

    No Known Activations