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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75137
    Prev
    Next
    INDEX
    Explanations

    references to software and technical products

    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
    Kansas
    -0.09
    Android
    -0.08
     Texas
    -0.08
     Oklahoma
    -0.08
     Edmonton
    -0.08
     Oilers
    -0.08
    ansas
    -0.08
     Android
    -0.07
    ürn
    -0.07
    _android
    -0.07
    POSITIVE LOGITS
     Apple
    0.12
     Mac
    0.11
     apple
    0.10
    .apple
    0.10
    Apple
    0.10
     plist
    0.10
     APPLE
    0.09
    .dylib
    0.09
    mac
    0.09
     apples
    0.09
    Activations Density 0.039%

    No Known Activations