© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89061
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal-formatted numeric tokens (floating-point numbers).

    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
    lenir
    -0.07
     Dropbox
    -0.06
    .Large
    -0.06
    viewController
    -0.06
     brutally
    -0.06
     Talk
    -0.06
     Standards
    -0.06
    culture
    -0.06
    ards
    -0.06
    uvwxyz
    -0.06
    POSITIVE LOGITS
     вигля
    0.07
    لة
    0.07
     гем
    0.06
    iw
    0.06
    level
    0.06
    ){//
    0.06
     dị
    0.06
     Derm
    0.06
     아래
    0.06
     реє
    0.06
    Activations Density 0.055%

    No Known Activations