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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 76072
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structural elements in technical documents

    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
    ahlen
    -0.08
     ãĤ¢ãĤ¤
    -0.06
    éĵģ
    -0.06
     Tray
    -0.06
     Termin
    -0.06
    ovah
    -0.06
     yaw
    -0.06
    root
    -0.06
     ballistic
    -0.06
    еÑĤÑĥ
    -0.06
    POSITIVE LOGITS
    InSection
    0.08
     TMPro
    0.07
     Carnegie
    0.07
    Associated
    0.06
    åIJĽ
    0.06
    баÑģ
    0.06
    LETTE
    0.06
    /xhtml
    0.06
    _queues
    0.06
    Ingredients
    0.06
    Activations Density 0.031%

    No Known Activations