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. 40549
    Prev
    Next
    INDEX
    Explanations

    enthusiastic

    np_max-act · gemini-2.0-flash

    The neuron activates on words expressing enthusiastic energy or excitement (e.g., “enthusiastic,” “enthusiasm,” “energetic”).

    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
     protects
    -0.07
    .life
    -0.06
    (grid
    -0.06
    .instance
    -0.06
    리는
    -0.06
     напрям
    -0.06
     protecting
    -0.06
     fixing
    -0.06
    BigDecimal
    -0.06
    idend
    -0.06
    POSITIVE LOGITS
     enthusiasm
    0.14
     enthusiasts
    0.10
     enthusiastic
    0.09
     enthus
    0.09
     enthusiast
    0.09
     enthusiastically
    0.08
    aneously
    0.08
     Erica
    0.07
     enthusi
    0.07
    hlas
    0.07
    Activations Density 0.005%

    No Known Activations