© 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. 119899
    Prev
    Next
    INDEX
    Explanations

    instances of timestamps or dates in various formats

    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
     dot
    -0.06
     um
    -0.06
     Bender
    -0.06
    apesh
    -0.06
    rypton
    -0.05
    ola
    -0.05
    åĩ¡
    -0.05
    tb
    -0.05
     f
    -0.05
    writers
    -0.05
    POSITIVE LOGITS
    uhl
    0.08
    isor
    0.07
    iyah
    0.07
    км
    0.07
    _drv
    0.07
    )prepare
    0.07
    odyn
    0.06
    enna
    0.06
    :UIAlert
    0.06
    LayoutParams
    0.06
    Activations Density 0.005%

    No Known Activations