Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126775
    Prev
    Next
    INDEX
    Explanations

    Forum/blog posts

    np_max-act · gemini-2.0-flash

    This neuron activates on German-language words or phrases.

    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
     ECS
    -0.07
    Pocket
    -0.06
     xảy
    -0.06
    ολ
    -0.06
    _ssl
    -0.06
    děpodob
    -0.06
    ользоват
    -0.06
    /hooks
    -0.06
    .node
    -0.06
    /meta
    -0.06
    POSITIVE LOGITS
    面议
    0.07
    _PIX
    0.06
     despre
    0.06
    Bluetooth
    0.06
     بیشتر
    0.06
     방
    0.06
     وفي
    0.06
    ensis
    0.06
    след
    0.06
     personnes
    0.06
    Activations Density 0.122%

    No Known Activations