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

    Neuronpedia

    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. 75946
    Prev
    Next
    INDEX
    Explanations

    references to education, resources, and support systems impacting future opportunities

    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
    abei
    -0.07
    riba
    -0.06
     Williamson
    -0.06
    GIS
    -0.06
    å½
    -0.06
     Starr
    -0.06
     mặt
    -0.06
     cata
    -0.06
     ÙħØ«
    -0.05
    lexible
    -0.05
    POSITIVE LOGITS
     continued
    0.13
     follow
    0.13
     post
    0.12
     continuing
    0.12
     continue
    0.11
     continues
    0.11
    continue
    0.10
     Post
    0.10
     after
    0.10
    continued
    0.10
    Activations Density 0.080%

    No Known Activations