© 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. 6752
    Prev
    Next
    INDEX
    Explanations

    scientific & mathematical contexts

    np_max-act · gemini-2.0-flash

    This neuron detects technical mathematical adjectives—particularly occurrences of “fractional” and “generalized.”

    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
    онт
    -0.07
     bottom
    -0.06
     concurrently
    -0.06
    PAGE
    -0.06
    rap
    -0.06
    UIL
    -0.06
     fiance
    -0.06
    什么
    -0.06
    请输入
    -0.06
     посад
    -0.06
    POSITIVE LOGITS
    sessionId
    0.07
     generalize
    0.07
     Muhammed
    0.07
    écial
    0.07
     fractional
    0.06
    _production
    0.06
     generalized
    0.06
     Heidi
    0.06
     edil
    0.06
     glVertex
    0.06
    Activations Density 0.002%

    No Known Activations