© 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. 15039
    Prev
    Next
    INDEX
    Explanations

    references to the Omicron variant of COVID-19

    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
    abby
    -0.06
    BAB
    -0.06
    .sap
    -0.06
    APTER
    -0.06
    ongyang
    -0.06
    lament
    -0.06
    paragus
    -0.06
    .LA
    -0.06
    PF
    -0.06
    Īĺ
    -0.05
    POSITIVE LOGITS
    æŀ
    0.07
    erk
    0.07
    phis
    0.06
    erdem
    0.06
    ogen
    0.06
     Arms
    0.06
    ron
    0.06
     station
    0.06
    etime
    0.06
    _ASSUME
    0.06
    Activations Density 0.010%

    No Known Activations