© 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. 93396
    Prev
    Next
    INDEX
    Explanations

    expressions related to temporal references and personal experiences

    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
     bisher
    -0.08
    soon
    -0.07
    ivar
    -0.07
    缮åīį
    -0.07
     soon
    -0.07
    ÏĦÏģ
    -0.07
    later
    -0.07
    844
    -0.06
     since
    -0.06
     later
    -0.06
    POSITIVE LOGITS
     similarly
    0.07
    eto
    0.07
    trand
    0.06
     wre
    0.06
     would
    0.06
     freshly
    0.06
     rot
    0.06
     Rowe
    0.06
    acon
    0.06
    thinkable
    0.06
    Activations Density 0.029%

    No Known Activations