© 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. 42714
    Prev
    Next
    INDEX
    Explanations

    dialogues/conversations

    np_max-act · gemini-2.0-flash

    This neuron activates on French-language tokens.

    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
    Tabs
    -0.07
    Quality
    -0.06
    pathname
    -0.06
     contradiction
    -0.06
     Har
    -0.06
     mirrored
    -0.06
    makers
    -0.06
    'h
    -0.06
    hosts
    -0.06
    urning
    -0.06
    POSITIVE LOGITS
     कम
    0.07
     Coleman
    0.06
    一级
    0.06
     nướng
    0.06
    ุร
    0.06
     Ülke
    0.06
     authService
    0.06
    一直
    0.06
    _cur
    0.06
     �
    0.06
    Activations Density 0.015%

    No Known Activations