© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68605
    Prev
    Next
    INDEX
    Explanations

    Hepatectomy

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the liver and related anatomical or procedural terms (e.g. liver regeneration, liver remnant, hepatic resection).

    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
     번째
    -0.06
     mohou
    -0.06
    -Muslim
    -0.06
     punching
    -0.06
    ectomy
    -0.06
    medium
    -0.06
     synthetic
    -0.06
     Sue
    -0.06
    اهی
    -0.06
    ._↵↵
    -0.06
    POSITIVE LOGITS
    Ess
    0.07
     νο
    0.07
    *dx
    0.07
    armac
    0.07
     inflatable
    0.07
     №
    0.06
     TimeUnit
    0.06
     edi
    0.06
    (retval
    0.06
     LA
    0.06
    Activations Density 0.005%

    No Known Activations