© 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. 82364
    Prev
    Next
    INDEX
    Explanations

    relational nouns and 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
     indeed
    -0.07
     thereby
    -0.06
     ultimately
    -0.06
    elerik
    -0.06
     totiž
    -0.06
     Indeed
    -0.06
     repeatedly
    -0.06
    jee
    -0.06
    yal
    -0.06
     reportedly
    -0.06
    POSITIVE LOGITS
     another
    0.11
     ebenfalls
    0.11
     similarly
    0.10
    another
    0.10
    åı¦ä¸Ģ
    0.10
     otro
    0.09
    ãģĵãģ¡ãĤī
    0.09
     yine
    0.09
    Another
    0.08
     equally
    0.08
    Activations Density 0.036%

    No Known Activations