© 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 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. 106662
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or duration

    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
    FX
    -0.07
     Gone
    -0.06
    ách
    -0.06
    ilib
    -0.06
    /Runtime
    -0.06
    ene
    -0.06
     upcoming
    -0.06
    try
    -0.06
    fx
    -0.06
     newfound
    -0.06
    POSITIVE LOGITS
     later
    0.13
    later
    0.12
     Later
    0.10
    Later
    0.10
     therefore
    0.10
     subsequently
    0.09
     später
    0.09
    åĽłæѤ
    0.09
    then
    0.08
    ï¼ĮåĽłæѤ
    0.08
    Activations Density 0.040%

    No Known Activations