© 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. 89169
    Prev
    Next
    INDEX
    Explanations

    node

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of cancer clinical measures—especially lymph node status—often expressed as numerical staging or metrics.

    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
    (camera
    -0.08
     thừa
    -0.07
     своїм
    -0.07
    ImageSharp
    -0.07
     Andrea
    -0.07
    (paren
    -0.06
     ($("#
    -0.06
    ていない
    -0.06
    _CHAIN
    -0.06
     cheer
    -0.06
    POSITIVE LOGITS
     envi
    0.07
    адження
    0.07
    .ev
    0.06
    енти
    0.06
     Environment
    0.06
     Liberal
    0.06
    ιν
    0.06
    Bug
    0.06
    _private
    0.06
    \.
    0.06
    Activations Density 0.004%

    No Known Activations