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. 84724
    Prev
    Next
    INDEX
    Explanations

    software testing

    np_max-act · gemini-2.0-flash

    This neuron fires on square‐bracketed attribute/annotation markers in code (e.g. “[Test]”, “[Fact]”, etc.).

    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
     Shutterstock
    -0.08
    Data
    -0.07
     잠
    -0.06
    间
    -0.06
    warnings
    -0.06
     데이터
    -0.06
    Emergency
    -0.06
    {
    -0.06
    解决
    -0.06
     Dent
    -0.06
    POSITIVE LOGITS
    .WebControls
    0.07
     Buttons
    0.06
    markt
    0.06
    .FindGameObjectWithTag
    0.06
    雷
    0.06
    ToMany
    0.06
    stants
    0.06
    -API
    0.06
    _family
    0.06
    -Pacific
    0.06
    Activations Density 0.006%

    No Known Activations