© 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. 128763
    Prev
    Next
    INDEX
    Explanations

    survival rates and prognosis

    np_max-act · gemini-2.0-flash

    medical terms related to cancer and its characteristics.

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

    This neuron selectively activates on numerical treatment outcome statistics, such as survival durations, percentages, and related quantifiers in clinical context.

    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
    lue
    -0.07
    ออก
    -0.06
     případně
    -0.06
     Paint
    -0.06
     png
    -0.06
    Bitmap
    -0.06
    Everything
    -0.06
    istogram
    -0.06
     independ
    -0.06
     nữa
    -0.06
    POSITIVE LOGITS
     shines
    0.08
    ً
    0.07
     법
    0.07
     LOT
    0.07
    misc
    0.06
     charset
    0.06
    鼠
    0.06
     Hearts
    0.06
    „
    0.06
     MEDIA
    0.06
    Activations Density 0.020%

    No Known Activations