© 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. 12791
    Prev
    Next
    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML/XML tag tokens (especially closing tags like “</div>”), i.e. it looks for markup bracketed elements.

    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
    аю
    -0.07
    dark
    -0.07
    仰
    -0.06
     paddingTop
    -0.06
     Dubai
    -0.06
    íl
    -0.06
    事
    -0.06
     Loft
    -0.06
    у
    -0.06
     Lav
    -0.06
    POSITIVE LOGITS
     привед
    0.07
    QUERY
    0.07
     آم
    0.06
     esk
    0.06
    /how
    0.06
    hta
    0.06
     giữ
    0.06
     chave
    0.06
    ратить
    0.06
     Ran
    0.06
    Activations Density 0.037%

    No Known Activations