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. 127410
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric tokens (i.e. numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to times and dates—especially numbers and punctuation like colons used in timecodes and other temporal markers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Hive
    -0.07
    .centerX
    -0.07
     VS
    -0.07
    alyze
    -0.07
    magic
    -0.07
     回
    -0.06
    unker
    -0.06
    inati
    -0.06
    .addChild
    -0.06
    िव
    -0.06
    POSITIVE LOGITS
    ليات
    0.06
    面议
    0.06
     kell
    0.06
     Validation
    0.06
     Structure
    0.06
     Population
    0.06
     hangi
    0.06
    "),↵↵
    0.06
     ),↵↵
    0.06
    ."),
    0.06
    Activations Density 0.360%

    No Known Activations