© 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. 128843
    Prev
    Next
    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash

    This neuron detects exponentiation notation (the “**” operator and its associated power expressions) in mathematical formulas.

    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
    чний
    -0.07
    された
    -0.07
     Arcade
    -0.07
    .strftime
    -0.07
    argout
    -0.07
     Celt
    -0.07
     varargin
    -0.06
     آدم
    -0.06
     Ruf
    -0.06
     Platt
    -0.06
    POSITIVE LOGITS
    ницип
    0.07
     좀
    0.06
     almost
    0.06
    juries
    0.06
    Lights
    0.06
     :]
    0.06
    eka
    0.06
     bleed
    0.06
     departure
    0.06
     
    0.06
    Activations Density 0.017%

    No Known Activations