© 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. 78098
    Prev
    Next
    INDEX
    Explanations

    references to tea preparation and processing methods

    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
    illet
    -0.07
    áp
    -0.07
    LAS
    -0.06
     Gulf
    -0.06
     plasma
    -0.06
     inject
    -0.06
     Memphis
    -0.06
     DJ
    -0.06
    urger
    -0.06
    Las
    -0.06
    POSITIVE LOGITS
     tea
    0.15
     Tea
    0.14
    tea
    0.13
     teas
    0.10
    èĮ¶
    0.10
     Ñĩай
    0.10
    oir
    0.08
    steam
    0.07
     caffeine
    0.07
     reste
    0.07
    Activations Density 0.015%

    No Known Activations