© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12963
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially numbers, decimal fractions, and percentages—highlighting where figures appear 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
    riba
    -0.07
     Movies
    -0.06
    werk
    -0.06
    mul
    -0.06
    gmail
    -0.06
     snapshots
    -0.06
    Reload
    -0.06
    ipples
    -0.06
    rière
    -0.06
    snapshot
    -0.06
    POSITIVE LOGITS
     slick
    0.07
     طبقه
    0.06
    .dart
    0.06
    .cljs
    0.06
    指数
    0.06
     ↵↵↵↵↵
    0.06
    _det
    0.06
     revolutionary
    0.06
    _GUID
    0.06
     Featured
    0.06
    Activations Density 0.010%

    No Known Activations