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. 86162
    Prev
    Next
    INDEX
    Explanations

    axios

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the “axios” library (and its related method calls) in code.

    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
    andum
    -0.08
     Trad
    -0.07
    urus
    -0.07
     magn
    -0.07
     lock
    -0.07
    енні
    -0.07
     درمان
    -0.07
    орту
    -0.07
    672
    -0.07
    _levels
    -0.07
    POSITIVE LOGITS
     axios
    0.10
     Axios
    0.09
    axios
    0.07
     Zwe
    0.06
     visualization
    0.06
     JOptionPane
    0.06
     đáng
    0.06
    esion
    0.06
     ApplicationContext
    0.06
    /@
    0.06
    Activations Density 0.001%

    No Known Activations