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. 42011
    Prev
    Next
    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    The neuron reliably lights up on HTML/XML tag tokens (i.e. angle‐bracketed markup elements like <!DOCTYPE>, <html>, <head>, <div>, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    HTML and JavaScript elements specific to structured documentation.

    oai_token-act-pair · gpt-4o-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
    Honda
    -0.07
     Fulton
    -0.07
     perpetrators
    -0.07
     Thompson
    -0.07
     scholarship
    -0.07
     puppet
    -0.07
    /kubernetes
    -0.07
    (factor
    -0.07
     transit
    -0.07
     Honda
    -0.06
    POSITIVE LOGITS
    adc
    0.06
    似乎
    0.06
     Не
    0.06
     airl
    0.06
    DAL
    0.06
    iyon
    0.06
     uphe
    0.06
    INATION
    0.06
    امة
    0.06
     Bags
    0.06
    Activations Density 0.008%

    No Known Activations