© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43270
    Prev
    Next
    INDEX
    Explanations

    Scotch

    np_max-act · gemini-2.0-flash

    This neuron responds to the word “whisky” (including its subparts like “wh” + “isky”) whenever it appears in the text.

    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
     bees
    -0.07
    人才
    -0.06
    /kg
    -0.06
    洲
    -0.06
     سازی
    -0.06
     algun
    -0.06
    .Service
    -0.06
    pagination
    -0.06
    jwt
    -0.06
     colormap
    -0.06
    POSITIVE LOGITS
     eu
    0.07
     ihtiy
    0.07
     इतन
    0.06
     discipline
    0.06
    great
    0.06
    แห
    0.06
     sucked
    0.06
     giúp
    0.06
    ronics
    0.06
    ponents
    0.06
    Activations Density 0.002%

    No Known Activations