© 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. 109484
    Prev
    Next
    INDEX
    Explanations

    Scientific/numerical data

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—especially decimal numbers and scientific-notation floats—highlighting where floating-point values 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
    -fiction
    -0.07
    .RequestBody
    -0.06
     balcony
    -0.06
    .Rectangle
    -0.06
     Hai
    -0.06
     Doing
    -0.06
     Barg
    -0.06
    -tax
    -0.06
    .Resolve
    -0.06
     footnote
    -0.06
    POSITIVE LOGITS
    委員
    0.07
     Hermes
    0.07
     모델
    0.06
    nbr
    0.06
     pilots
    0.06
     contacting
    0.06
    χεί
    0.06
    UTIL
    0.06
    .path
    0.06
    Touch
    0.06
    Activations Density 0.027%

    No Known Activations