© 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. 91739
    Prev
    Next
    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric literal tokens (especially floating-point constants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code structures related to user interface components in SwiftUI applications.

    oai_token-act-pair · gpt-4o-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
    (Render
    -0.07
     Numeric
    -0.07
     为
    -0.06
     terrace
    -0.06
     captured
    -0.06
    Hol
    -0.06
     Shim
    -0.06
    Spec
    -0.06
     juven
    -0.06
     então
    -0.06
    POSITIVE LOGITS
    щих
    0.06
     fifo
    0.06
     вет
    0.06
     teste
    0.06
    화
    0.05
     posicion
    0.05
    lli
    0.05
     broadcasting
    0.05
    шив
    0.05
     radioactive
    0.05
    Activations Density 0.001%

    No Known Activations