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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57564
    Prev
    Next
    INDEX
    Explanations

    references to playful or interactive products

    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
    ancel
    -0.06
     Robin
    -0.06
    oven
    -0.06
    ardi
    -0.06
     ord
    -0.06
    387
    -0.06
    _OPENGL
    -0.06
     soul
    -0.06
    mant
    -0.05
     Guy
    -0.05
    POSITIVE LOGITS
    abox
    0.07
    æı¡
    0.07
     toys
    0.07
    eya
    0.07
    uro
    0.07
    otyp
    0.07
     helicopt
    0.07
    afe
    0.07
     ÑģодеÑĢж
    0.07
    ges
    0.07
    Activations Density 0.003%

    No Known Activations