Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93032
    Prev
    Next
    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “math” library (including “cmath”) in code.

    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
    ουλ
    -0.06
    Ocean
    -0.06
     �
    -0.06
    totalCount
    -0.06
    RoleId
    -0.06
    وی
    -0.06
    _literal
    -0.06
    보험
    -0.06
    รษฐ
    -0.05
     occas
    -0.05
    POSITIVE LOGITS
     farmhouse
    0.07
    emos
    0.07
     خانه
    0.07
    IENCE
    0.07
     musicians
    0.06
    -------------
    0.06
    _NS
    0.06
    -shaped
    0.06
    ____________
    0.06
     kms
    0.06
    Activations Density 0.003%

    No Known Activations