© 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. 85966
    Prev
    Next
    INDEX
    Explanations

    horse racing

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of stakes‐race events—i.e. occurrences of “Stakes” (often alongside purse amounts or distances) in racing write-ups.

    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
     Approval
    -0.07
     approval
    -0.07
     мон
    -0.07
    칠
    -0.07
    plant
    -0.06
    iseum
    -0.06
    ufs
    -0.06
    Semaphore
    -0.06
     اختلاف
    -0.06
    OneToMany
    -0.06
    POSITIVE LOGITS
     toll
    0.07
     ;
↵
    0.06
     multinational
    0.06
    _v
    0.06
     gigg
    0.06
    _w
    0.06
     tasty
    0.06
     alien
    0.06
     capitalized
    0.06
     chopped
    0.06
    Activations Density 0.005%

    No Known Activations