© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    references to durations of time, specifically years and months

    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
    ube
    -0.06
    yd
    -0.06
    seen
    -0.06
    wyn
    -0.06
     Doub
    -0.06
     aktu
    -0.05
    æĴ
    -0.05
     reciprocal
    -0.05
     universal
    -0.05
     Jelly
    -0.05
    POSITIVE LOGITS
    ugins
    0.07
     Singular
    0.07
     diet
    0.06
     boyunca
    0.06
    abytes
    0.06
     sine
    0.06
    ìĥģ
    0.06
    jde
    0.06
    âķĹ
    0.06
    diet
    0.06
    Activations Density 0.029%

    No Known Activations