Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130306
    Prev
    Next
    INDEX
    Explanations

    pl

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of total knee arthroplasty (e.g., “TKA” or “total knee arthroplasty”).

    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
    uppen
    -0.06
     perfume
    -0.06
    _bold
    -0.06
    campo
    -0.06
     OTHER
    -0.06
     Exterior
    -0.06
     crow
    -0.06
     Alps
    -0.06
     İlk
    -0.06
    _bad
    -0.06
    POSITIVE LOGITS
    IFn
    0.07
    oplast
    0.07
     林
    0.06
    incr
    0.06
     Integer
    0.06
    خصص
    0.06
     cro
    0.06
    arParams
    0.06
     Marijuana
    0.06
    енням
    0.06
    Activations Density 0.002%

    No Known Activations