© 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. 12539
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on numeric literal tokens (numbers, including integers and floats) in code snippets.

    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
     ANN
    -0.07
     cheapest
    -0.07
    infile
    -0.07
    بيع
    -0.07
    InSection
    -0.07
    .DOWN
    -0.07
     Александ
    -0.06
    rex
    -0.06
    بش
    -0.06
     xa
    -0.06
    POSITIVE LOGITS
     体
    0.07
     Trick
    0.06
     lượng
    0.06
    ляет
    0.06
    __;
    0.06
    -school
    0.06
     Colleg
    0.06
    �
    0.06
    ступ
    0.06
    ku
    0.06
    Activations Density 0.033%

    No Known Activations