© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13377
    Prev
    Next
    INDEX
    Explanations

    plays

    np_max-act · gemini-2.0-flash

    This neuron detects the “plays for” phrase that introduces a player’s current club affiliation.

    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
     красив
    -0.07
     biom
    -0.07
    _elements
    -0.07
     isConnected
    -0.06
     přip
    -0.06
     emulation
    -0.06
    一样
    -0.06
     mattress
    -0.06
    Connections
    -0.06
    症
    -0.06
    POSITIVE LOGITS
     Tin
    0.07
     müc
    0.06
     sine
    0.06
     sabah
    0.06
    ="${
    0.06
    OSP
    0.06
     kart
    0.06
    YE
    0.06
    976
    0.06
    hpp
    0.06
    Activations Density 0.007%

    No Known Activations