© 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. 30463
    Prev
    Next
    INDEX
    Explanations

    ine

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “purine” (often in biochemical terms like purine nucleotides, purine bases, or purine metabolism).

    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
    .Dimension
    -0.08
     toolStrip
    -0.07
    graphics
    -0.07
     karar
    -0.07
    .DockStyle
    -0.07
     ################################################################
    -0.06
     чуть
    -0.06
     эффектив
    -0.06
     біля
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    hip
    0.07
     grep
    0.07
     mut
    0.07
    �
    0.07
    Mus
    0.07
     cous
    0.06
    .LoggerFactory
    0.06
    krit
    0.06
    ┃
    0.06
     prefixed
    0.06
    Activations Density 0.009%

    No Known Activations