© 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. 12618
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting numeric or measurement expressions enclosed in parentheses (e.g., quantitative values or parameter labels).

    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
    otics
    -0.07
    setOnClickListener
    -0.07
     pund
    -0.07
     LV
    -0.07
     详情
    -0.06
     आई
    -0.06
     Waist
    -0.06
     bak
    -0.06
    Assets
    -0.06
    amar
    -0.06
    POSITIVE LOGITS
     sitting
    0.06
    'in
    0.06
     Locke
    0.06
    ild
    0.06
    >Description
    0.06
     CGI
    0.06
     unus
    0.05
    rain
    0.05
    starts
    0.05
    .system
    0.05
    Activations Density 0.041%

    No Known Activations