© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38642
    Prev
    Next
    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash

    references to diplomatic tensions and international relations issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to mentions of intelligence information exchange—especially words like “intelligence,” “information,” “sharing,” “notifying,” or “relaying.”

    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
    zbollah
    -0.07
    atisch
    -0.07
     کارخانه
    -0.07
     ‎
    -0.07
    CppGeneric
    -0.06
     harassed
    -0.06
     ≤
    -0.06
    {x
    -0.06
     和
    -0.06
     Thunder
    -0.06
    POSITIVE LOGITS
     ancestral
    0.07
    فة
    0.06
    /categories
    0.06
    اسم
    0.06
     appId
    0.06
     tvoří
    0.06
     fopen
    0.06
     skuteč
    0.06
    istrar
    0.06
     Venus
    0.06
    Activations Density 0.142%

    No Known Activations