© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92359
    Prev
    Next
    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash

    This neuron activates on the token “Location” (as in “Location 1” or “Location 2”), i.e. when the model is naming a candidate location choice in the navigation dialogue.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    descriptions of locations or settings.

    oai_token-act-pair · gpt-4o-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
    bp
    -0.07
     especialmente
    -0.06
     commitment
    -0.06
     درخواست
    -0.06
     ارزی
    -0.06
     handwritten
    -0.06
     میلادی
    -0.06
     fiat
    -0.06
     rhs
    -0.06
    alaria
    -0.06
    POSITIVE LOGITS
     SOUTH
    0.07
     intersect
    0.06
    &amp
    0.06
    лки
    0.06
     kadın
    0.06
    ymology
    0.06
     Juni
    0.06
    (class
    0.06
    (year
    0.06
    viewer
    0.06
    Activations Density 0.044%

    No Known Activations