© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90637
    Prev
    Next
    INDEX
    Explanations

    method calls and data retrieval functions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utz
    -0.06
    åĸ
    -0.06
    ạ
    -0.06
    åĭ
    -0.06
     Han
    -0.06
    orra
    -0.06
    Coverage
    -0.05
     rarity
    -0.05
    wg
    -0.05
    icum
    -0.05
    POSITIVE LOGITS
    hek
    0.08
    449
    0.08
    ter
    0.07
    948
    0.07
    tern
    0.06
    ниÑĨа
    0.06
    284
    0.06
    enu
    0.06
    rames
    0.06
    apolis
    0.06
    Activations Density 0.020%

    No Known Activations