© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124438
    Prev
    Next
    INDEX
    Explanations

    septic

    np_max-act · gemini-2.0-flash

    medical terminology related to bacterial infections.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of sepsis‐related medical conditions (the term “septic” as used in infection contexts).

    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
     delay
    -0.07
     мала
    -0.07
    である
    -0.06
    .Con
    -0.06
     genomes
    -0.06
    asis
    -0.06
    colo
    -0.06
     recordings
    -0.06
    Devices
    -0.06
    ウ
    -0.06
    POSITIVE LOGITS
     vegetable
    0.08
    ุธ
    0.07
    /bit
    0.07
     Mystic
    0.07
     Ston
    0.06
     VIC
    0.06
    .getComponent
    0.06
     yık
    0.06
    �
    0.06
     bitk
    0.06
    Activations Density 0.001%

    No Known Activations