© 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. 91530
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens—especially decimal or fractional 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
    Anything
    -0.06
    .deltaTime
    -0.06
    >%
    -0.06
    edList
    -0.06
     currentTime
    -0.06
    行政
    -0.06
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.06
     inconvenience
    -0.06
     бал
    -0.06
    runs
    -0.06
    POSITIVE LOGITS
     internationally
    0.07
    價
    0.06
     gaping
    0.06
    lanma
    0.06
     Manufact
    0.06
     understandably
    0.06
    mission
    0.06
     Domain
    0.05
     нада
    0.05
    今日
    0.05
    Activations Density 0.557%

    No Known Activations