© 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. 69668
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between quantities or outcomes

    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
    azer
    -0.08
    Enlarge
    -0.07
    esen
    -0.07
    åĶ¯
    -0.07
    foy
    -0.07
    errupted
    -0.06
    Ñıви
    -0.06
    ä¸įäºĨ
    -0.06
    	TokenName
    -0.06
    еÑĢг
    -0.06
    POSITIVE LOGITS
     entire
    0.14
     whole
    0.12
     lifetime
    0.12
     entirety
    0.10
     lifelong
    0.09
    whole
    0.09
    æķ´ä¸ª
    0.09
    lifetime
    0.09
     Lifetime
    0.09
     throughout
    0.08
    Activations Density 0.011%

    No Known Activations