© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126780
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    The neuron is tuned to pick out numeric tokens that denote citation details (e.g. journal volume and page numbers) in the reference sections.

    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
     Ice
    -0.08
     sleep
    -0.08
     Water
    -0.08
     footh
    -0.07
     occurred
    -0.07
     paper
    -0.07
     Sept
    -0.07
     oc
    -0.07
     trẻ
    -0.07
     مه
    -0.07
    POSITIVE LOGITS
    465
    0.09
    567
    0.08
    463
    0.08
    165
    0.08
    464
    0.08
    263
    0.08
    269
    0.08
    762
    0.08
    861
    0.07
    765
    0.07
    Activations Density 0.150%

    No Known Activations