© 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. 30199
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects etiology statements in biomedical text—especially “caused by” phrases that name the disease‐causing pathogen.

    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
     문화
    -0.07
    thickness
    -0.07
    .ta
    -0.06
     mirrors
    -0.06
     говорить
    -0.06
    추천
    -0.06
    -window
    -0.06
     Над
    -0.06
    Repeated
    -0.06
     literature
    -0.06
    POSITIVE LOGITS
     nip
    0.07
    （笑
    0.06
     brew
    0.06
    ingular
    0.06
    installer
    0.06
     oauth
    0.06
    uddle
    0.06
    [loc
    0.06
     开
    0.06
    inheritdoc
    0.06
    Activations Density 0.009%

    No Known Activations