© 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. 95243
    Prev
    Next
    INDEX
    Explanations

    temporal references related to future projections and commitments

    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
    ihn
    -0.07
    .scalajs
    -0.07
     Kür
    -0.07
    걸
    -0.07
     recent
    -0.07
    ç°
    -0.07
    _regeneration
    -0.07
    weeks
    -0.07
    timeofday
    -0.07
     STATS
    -0.07
    POSITIVE LOGITS
    203
    0.10
     beyond
    0.10
     years
    0.09
     Beyond
    0.08
     decade
    0.08
    202
    0.08
    Beyond
    0.07
     future
    0.07
    ipl
    0.07
     Years
    0.07
    Activations Density 0.025%

    No Known Activations