© 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. 78097
    Prev
    Next
    INDEX
    Explanations

    biopsy

    np_max-act · gemini-2.0-flash

    medical terms related to renal and vascular conditions.

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

    The neuron selectively detects mentions of “biopsy” (and its morphological variants like biopsy-proven or biopsies) indicating tissue‐sampling 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
    MMC
    -0.07
    	stream
    -0.06
    _func
    -0.06
    KW
    -0.06
    .cfg
    -0.06
     strftime
    -0.06
     Numbers
    -0.06
    _statement
    -0.06
    丝
    -0.06
    _polygon
    -0.06
    POSITIVE LOGITS
     biopsy
    0.14
     yc
    0.07
     autopsy
    0.07
    opsy
    0.07
     me
    0.07
     weighing
    0.07
    해보
    0.07
    πι
    0.07
    _ir
    0.07
     anytime
    0.07
    Activations Density 0.003%

    No Known Activations