© 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. 17-LLAMASCOPE-RES-131K
    11. 30353
    Prev
    Next
    INDEX
    Explanations

    words related to the passage of time or durations

    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
     se
    -0.06
    bow
    -0.06
    igon
    -0.06
    cker
    -0.06
     Wal
    -0.06
    hdl
    -0.06
    μοÏģ
    -0.06
    IRC
    -0.06
    nad
    -0.06
    _exempt
    -0.06
    POSITIVE LOGITS
    reverse
    0.07
    RF
    0.06
    853
    0.06
    LOPT
    0.06
    ylan
    0.06
    ACHI
    0.06
    RT
    0.06
    alin
    0.06
    æ½®
    0.06
     Reverse
    0.06
    Activations Density 0.006%

    No Known Activations