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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 85887
    Prev
    Next
    INDEX
    Explanations

    Creating and actions

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not respond to any 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
     filmpjes
    -0.06
     захисту
    -0.06
    .Chart
    -0.06
     Winter
    -0.06
    _pushButton
    -0.06
     UT
    -0.06
     playa
    -0.06
    cell
    -0.06
     دانش
    -0.05
    /course
    -0.05
    POSITIVE LOGITS
    "k
    0.07
     evid
    0.06
    ไม
    0.06
    ті
    0.06
     IPAddress
    0.06
    .dart
    0.06
     bedroom
    0.06
    男性
    0.06
     ​​
    0.06
    研究所
    0.06
    Activations Density 0.001%

    No Known Activations