© 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. 15011
    Prev
    Next
    INDEX
    Explanations

    mentions of events and their scheduling details

    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
    286
    -0.07
    andest
    -0.07
    stin
    -0.07
    Signing
    -0.06
    adesh
    -0.06
    ież
    -0.06
    ampoo
    -0.06
     TOD
    -0.06
    leston
    -0.06
     Mondays
    -0.06
    POSITIVE LOGITS
     bew
    0.07
    wer
    0.07
    held
    0.07
    thren
    0.07
     vacc
    0.07
    -basket
    0.06
    ÄĽli
    0.06
    ÏĬ
    0.06
     annually
    0.06
     Vak
    0.06
    Activations Density 0.034%

    No Known Activations