© 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. 39169
    Prev
    Next
    INDEX
    Explanations

    days of the week and related time references

    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
    aja
    -0.06
     reins
    -0.06
    ult
    -0.05
     Bowling
    -0.05
     Monetary
    -0.05
     Earl
    -0.05
     nowhere
    -0.05
    ank
    -0.05
     mapa
    -0.05
    _errno
    -0.05
    POSITIVE LOGITS
    ktop
    0.09
    ubi
    0.08
    ivi
    0.07
    ernes
    0.07
    NES
    0.07
    blend
    0.07
    ngör
    0.07
    utsch
    0.07
    ubl
    0.07
    esus
    0.07
    Activations Density 0.016%

    No Known Activations