© 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. 91690
    Prev
    Next
    INDEX
    Explanations

    survival

    np_max-act · gemini-2.0-flash

    This neuron detects clinical‐outcome terms—especially words related to survival, prognosis, and prognostic significance.

    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
     Alexandre
    -0.08
    'on
    -0.07
     burge
    -0.06
     lesbienne
    -0.06
    (media
    -0.06
    istrar
    -0.06
     pantry
    -0.06
    宝
    -0.06
    piar
    -0.06
     широк
    -0.06
    POSITIVE LOGITS
    ília
    0.08
    تن
    0.06
    ように
    0.06
    양
    0.06
    ая
    0.06
     allocation
    0.06
    ابعة
    0.06
     spiritual
    0.06
     德
    0.06
    -program
    0.06
    Activations Density 0.008%

    No Known Activations