© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128285
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and scheduling

    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
    yo
    -0.07
    jid
    -0.06
    辺
    -0.06
    plib
    -0.06
    yth
    -0.06
    ador
    -0.06
    373
    -0.06
    lint
    -0.06
    ADOR
    -0.06
    visor
    -0.06
    POSITIVE LOGITS
     remaining
    0.10
    remaining
    0.09
     Remaining
    0.09
    åī©
    0.08
    ä¸ĭåİ»
    0.07
     season
    0.07
    Remaining
    0.07
    ihan
    0.07
    _remaining
    0.07
     finish
    0.07
    Activations Density 0.019%

    No Known Activations