© 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. 84245
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasons or justifications

    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
    inecraft
    -0.07
    yang
    -0.07
    -dot
    -0.07
    Interop
    -0.07
    ÑıÑģ
    -0.06
    onth
    -0.06
    /open
    -0.06
    means
    -0.06
    _DX
    -0.06
    merce
    -0.06
    POSITIVE LOGITS
     why
    0.11
    why
    0.08
     needing
    0.07
     Why
    0.07
    Why
    0.07
     being
    0.07
     success
    0.07
     WHY
    0.07
    为ä»Ģä¹Ī
    0.07
     not
    0.06
    Activations Density 0.011%

    No Known Activations