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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 81361
    Prev
    Next
    INDEX
    Explanations

    los

    np_max-act · gemini-2.0-flash

    This neuron detects the names of specific biological or chemical hazards (e.g. pathogens, toxins, and contaminants).

    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
     lai
    -0.07
    ализа
    -0.07
    (bucket
    -0.07
     suất
    -0.06
    есть
    -0.06
     ejected
    -0.06
    AE
    -0.06
     Convenient
    -0.06
     gated
    -0.06
     flagged
    -0.06
    POSITIVE LOGITS
     >↵
    0.07
     myriad
    0.06
    """↵
    0.06
    stretch
    0.06
     nachází
    0.06
    =↵
    0.06
     Mayıs
    0.06
    couldn
    0.06
    .Abstract
    0.06
    composer
    0.06
    Activations Density 0.031%

    No Known Activations