© 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
    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. 55403
    Prev
    Next
    INDEX
    Explanations

    UFC

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the UFC promotion—either its abbreviation “UFC” or the full phrase “Ultimate Fighting Championship.”

    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
    pageTitle
    -0.07
    enou
    -0.07
    LEV
    -0.06
     Lev
    -0.06
     Hasan
    -0.06
    	now
    -0.06
    compat
    -0.06
     dynamically
    -0.06
    Finance
    -0.06
    固定
    -0.06
    POSITIVE LOGITS
     UFC
    0.08
     infr
    0.06
     accomplished
    0.06
     overriding
    0.06
    /conf
    0.06
    /copyleft
    0.06
    .toCharArray
    0.06
     doby
    0.06
     dolar
    0.06
     pics
    0.06
    Activations Density 0.001%

    No Known Activations