© 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. 8975
    Prev
    Next
    INDEX
    Explanations

    separators

    np_max-act · gemini-2.0-flash

    This neuron responds to technical biomedical methods and measurement terms (e.g., assay names, tissue sampling, and analytical procedures).

    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
     �
    -0.06
    ジョ
    -0.06
     Destination
    -0.06
     Catch
    -0.06
     اطلاع
    -0.06
    converted
    -0.06
     Myers
    -0.06
     testCase
    -0.06
     dissect
    -0.06
     sho
    -0.06
    POSITIVE LOGITS
     законом
    0.08
    三级
    0.07
     Telegraph
    0.07
     slider
    0.06
     zásob
    0.06
     angered
    0.06
    .TextEdit
    0.06
    ře
    0.06
    childNodes
    0.06
    688
    0.06
    Activations Density 0.180%

    No Known Activations