© 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. 69368
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash

    The neuron detects structural/formatting elements in the document—things like headers, list or section numbers, and other layout tokens that mark sections or metadata.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    %.
    -0.07
    .wh
    -0.06
    Naming
    -0.06
    
    -0.06
     striking
    -0.06
    Partial
    -0.06
     pedigree
    -0.06
    省
    -0.06
    (im
    -0.06
    ("@
    -0.06
    POSITIVE LOGITS
     uprav
    0.07
     sek
    0.07
     Args
    0.06
     phát
    0.06
    “She
    0.06
    (ec
    0.06
     ([]
    0.06
     elephants
    0.06
     조사
    0.06
     researched
    0.06
    Activations Density 0.141%

    No Known Activations