© 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. 70894
    Prev
    Next
    INDEX
    Explanations

    references to chewing and related actions or products

    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
    rish
    -0.07
    zem
    -0.07
    ãĥ«ãĤ¯
    -0.07
    opus
    -0.06
     bow
    -0.06
    oli
    -0.06
    cert
    -0.06
    æµ´
    -0.06
    bow
    -0.06
     IPL
    -0.06
    POSITIVE LOGITS
     chew
    0.14
     chewing
    0.13
     spit
    0.10
     Chew
    0.10
     saliva
    0.09
     Spit
    0.08
     Vig
    0.08
     gum
    0.07
    bsite
    0.06
     cud
    0.06
    Activations Density 0.007%

    No Known Activations