© 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. 92643
    Prev
    Next
    INDEX
    Explanations

    Kayak

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of kayaking or stand-up paddleboarding (i.e. “kayak”- and “paddle”-related words).

    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
    ації
    -0.08
    ิท
    -0.07
    Profiles
    -0.07
    .application
    -0.06
     memor
    -0.06
     адрес
    -0.06
    -gap
    -0.06
     Evo
    -0.06
     espionage
    -0.06
     monsters
    -0.06
    POSITIVE LOGITS
     kayak
    0.10
     canoe
    0.09
    Say
    0.08
    igail
    0.07
    Kay
    0.07
    Last
    0.07
    say
    0.07
     Screw
    0.07
     cosy
    0.06
    &M
    0.06
    Activations Density 0.003%

    No Known Activations