© 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 EvalsExportsinterp-engineNEWAPI 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. 72024
    Prev
    Next
    INDEX
    Explanations

    structured data attributes and programming-related terms

    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
     Cannon
    -0.06
     subs
    -0.06
     Bucc
    -0.06
     gleich
    -0.05
     Emerging
    -0.05
     conven
    -0.05
    E
    -0.05
     sweep
    -0.05
     ecc
    -0.05
    ette
    -0.05
    POSITIVE LOGITS
    ocking
    0.10
    HDR
    0.08
    ertino
    0.08
     киÑģ
    0.08
    Marshal
    0.08
    MainFrame
    0.08
    _HDR
    0.08
    ibt
    0.08
    EventManager
    0.07
    ToFit
    0.07
    Activations Density 0.001%

    No Known Activations