© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75892
    Prev
    Next
    INDEX
    Explanations

    terms related to enhancements or advancements in various contexts

    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
    ebek
    -0.08
    kest
    -0.08
    vic
    -0.07
     Rut
    -0.07
     Buen
    -0.07
    uff
    -0.07
    KER
    -0.07
    nis
    -0.07
    ìŀĦ
    -0.07
     incompet
    -0.07
    POSITIVE LOGITS
    ment
    0.09
    /add
    0.08
    /update
    0.08
    -quality
    0.08
    ments
    0.07
    vements
    0.07
    etta
    0.07
    ohl
    0.07
    ative
    0.07
     chances
    0.07
    Activations Density 0.019%

    No Known Activations