© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86380
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically indicating temporal phrases related to "last" and "next"

    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
    adden
    -0.07
    notify
    -0.07
     Halloween
    -0.07
    subscribe
    -0.07
     Pry
    -0.06
    oretical
    -0.06
    aber
    -0.06
    atcher
    -0.06
     Thanksgiving
    -0.06
    typeof
    -0.06
    POSITIVE LOGITS
     Bowman
    0.07
    çļĦå¿ĥ
    0.06
    Ùħت
    0.06
    åīįçļĦ
    0.06
    facility
    0.06
    å®ļçļĦ
    0.06
    hap
    0.06
    esterday
    0.06
    å¹´çļĦ
    0.06
    à§įà¦
    0.06
    Activations Density 0.006%

    No Known Activations