© 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. 4463
    Prev
    Next
    INDEX
    Explanations

    proper names of authors and researchers

    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
    /disable
    -0.08
    Ãły
    -0.07
    ebe
    -0.07
    ار
    -0.07
    Ñĩили
    -0.07
    .cf
    -0.07
     plu
    -0.07
    ãģ£ãģ
    -0.07
    alis
    -0.06
    aiser
    -0.06
    POSITIVE LOGITS
    ostel
    0.07
     ÎļÏįÏĢ
    0.06
     Uncategorized
    0.06
    âĢ²
    0.06
    /frontend
    0.06
    othy
    0.06
    ahoma
    0.06
    âĢ¦↵
    0.06
    antwort
    0.06
    олай
    0.06
    Activations Density 0.001%

    No Known Activations