© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    references to historical narratives and contextual details

    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
    íݸ
    -0.07
    istrovstvÃŃ
    -0.06
    mage
    -0.06
    endir
    -0.06
     VÅ¡ech
    -0.06
    lescope
    -0.06
     afterward
    -0.06
     Already
    -0.06
    átek
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    POSITIVE LOGITS
     originally
    0.17
     formerly
    0.17
     initially
    0.15
     earlier
    0.15
     former
    0.14
    æĽ¾
    0.14
    formerly
    0.13
     original
    0.13
     سابÙĤ
    0.13
     Former
    0.13
    Activations Density 0.042%

    No Known Activations