© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    references to programming and mathematical computations, including variables, functions, and equations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is keyed to numeric literals—especially decimal numbers—typically in assignment statements (e.g. “var = 2.58”).

    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
     mains
    -0.07
     Painting
    -0.06
     drowning
    -0.06
     لی
    -0.06
     format
    -0.06
     chilly
    -0.06
    Volumes
    -0.06
    dül
    -0.06
    Upload
    -0.06
     surplus
    -0.06
    POSITIVE LOGITS
    ام
    0.07
    رى
    0.07
    rear
    0.06
    URLOPT
    0.06
     secretion
    0.06
     calcular
    0.06
    اقل
    0.06
    کنون
    0.06
     empleado
    0.06
    ري
    0.06
    Activations Density 0.017%

    No Known Activations