© 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. 28644
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant events or achievements

    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
    ÏĥÏħ
    -0.07
    voor
    -0.07
    future
    -0.06
    åħ·ä½ĵ
    -0.06
    عت
    -0.06
    on
    -0.06
    ìŀĦ
    -0.06
    .opts
    -0.06
    çŀ¬
    -0.06
    à¥Ĥन
    -0.06
    POSITIVE LOGITS
    åĿª
    0.07
    661
    0.07
    CSI
    0.07
    TypeInfo
    0.07
    άλι
    0.07
    uai
    0.06
    áz
    0.06
     tiers
    0.06
    alyzed
    0.06
    ég
    0.06
    Activations Density 0.031%

    No Known Activations