© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time and its impact on relevance and memory

    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
    icontrol
    -0.07
    ierge
    -0.07
    è¿ij
    -0.07
    _SCL
    -0.07
     Äijá»ĵng
    -0.07
     refresh
    -0.06
    itler
    -0.06
    ãĤīãģĹãģĦ
    -0.06
    arend
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    POSITIVE LOGITS
     future
    0.11
    future
    0.10
     someday
    0.09
     tomorrow
    0.08
     budou
    0.08
    Future
    0.08
    indsight
    0.08
     Future
    0.08
    .future
    0.08
     futuro
    0.07
    Activations Density 0.026%

    No Known Activations