© 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
    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. 839
    Prev
    Next
    INDEX
    Explanations

    page numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric strings and structured alphanumeric identifiers (e.g., docket numbers, document IDs, and page or case citations).

    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
     contours
    -0.06
    كون
    -0.06
     appName
    -0.06
    retty
    -0.06
     conduit
    -0.06
    ọc
    -0.06
    自动
    -0.06
    parsers
    -0.06
     Cancel
    -0.06
    getEmail
    -0.06
    POSITIVE LOGITS
     både
    0.07
    Elizabeth
    0.07
    	bus
    0.06
    °N
    0.06
     Leipzig
    0.06
     Reve
    0.06
     ایجاد
    0.06
     Eleven
    0.06
    845
    0.06
    判断
    0.06
    Activations Density 0.002%

    No Known Activations