© 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. 15-LLAMASCOPE-RES-131K
    11. 89163
    Prev
    Next
    INDEX
    Explanations

    references to programming tools or libraries

    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
    ãĥ£
    -0.07
    ar
    -0.07
    емон
    -0.07
    ngo
    -0.07
    lle
    -0.07
    agh
    -0.07
    agra
    -0.06
    živ
    -0.06
    lej
    -0.06
    esi
    -0.06
    POSITIVE LOGITS
    ä¹İ
    0.07
    ancel
    0.07
    ansion
    0.06
    upplier
    0.06
    irst
    0.06
    .www
    0.06
    GUID
    0.06
    vester
    0.06
    upported
    0.06
    chia
    0.06
    Activations Density 0.000%

    No Known Activations