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. 40629
    Prev
    Next
    INDEX
    Explanations

    hockey

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of the sport “hockey,” especially the phrase “ice hockey.”

    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
    alim
    -0.07
    .Dialog
    -0.07
    πουργ
    -0.07
    Clar
    -0.06
    (generator
    -0.06
     substit
    -0.06
     Nd
    -0.06
    елем
    -0.06
    806
    -0.06
    asına
    -0.06
    POSITIVE LOGITS
     hockey
    0.13
     Hockey
    0.11
     puck
    0.10
     hx
    0.09
     NHL
    0.07
     Hatch
    0.07
     team
    0.07
     discrimin
    0.07
     mHandler
    0.06
     Pick
    0.06
    Activations Density 0.002%

    No Known Activations