© 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. 83903
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in context

    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
     recently
    -0.11
     recent
    -0.10
     yesterday
    -0.10
     tomorrow
    -0.10
     tonight
    -0.09
    recent
    -0.09
     ì§ĢëĤľ
    -0.09
    ä»Ĭå¹´
    -0.09
     lately
    -0.09
    æľĢè¿ij
    -0.08
    POSITIVE LOGITS
     coinc
    0.07
    便
    0.06
    ogan
    0.06
     ÙħÛĮÙĦادÛĮ
    0.05
     Harden
    0.05
    rys
    0.05
     coincide
    0.05
    seo
    0.05
    oyal
    0.05
    occasion
    0.05
    Activations Density 0.095%

    No Known Activations