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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56961
    Prev
    Next
    INDEX
    Explanations

    terms related to time, specifically referencing previous or future events

    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
    inal
    -0.07
    .newBuilder
    -0.06
    ãģ¾ãģļ
    -0.06
    LineColor
    -0.06
     ï
    -0.06
    oppel
    -0.06
    issen
    -0.06
    .kode
    -0.06
    ãģŁãĤģãģ®
    -0.06
    HELL
    -0.06
    POSITIVE LOGITS
     generations
    0.08
    /current
    0.07
     versions
    0.07
    -generation
    0.07
    ilty
    0.07
     iterations
    0.07
    avery
    0.07
    ones
    0.07
     editions
    0.07
    odom
    0.06
    Activations Density 0.016%

    No Known Activations