© 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 EvalsExportsAPI 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. 29211
    Prev
    Next
    INDEX
    Explanations

    references to dates or periods in time

    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
    uiten
    -0.06
    vey
    -0.06
     zip
    -0.06
    chaft
    -0.06
    lez
    -0.06
    обÑĢаз
    -0.06
     Vill
    -0.06
     trait
    -0.06
     rer
    -0.06
    anches
    -0.06
    POSITIVE LOGITS
    arel
    0.08
    ReuseIdentifier
    0.07
     Franti
    0.07
    íĦ
    0.07
    /downloads
    0.07
    empt
    0.06
     Helmet
    0.06
    Å¡ov
    0.06
    uct
    0.06
    orWhere
    0.06
    Activations Density 0.000%

    No Known Activations