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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73407
    Prev
    Next
    INDEX
    Explanations

    concepts related to community-driven events and organizations

    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
    utsch
    -0.07
     seri
    -0.07
    anou
    -0.06
    ocode
    -0.06
    raya
    -0.06
     Demir
    -0.06
    calar
    -0.06
    olicit
    -0.06
    ï¸
    -0.06
    raki
    -0.06
    POSITIVE LOGITS
     independent
    0.15
     independently
    0.13
     independ
    0.13
    Independent
    0.13
    çĭ¬ç«ĭ
    0.12
    -independent
    0.12
     Independent
    0.11
     Independ
    0.11
    Independ
    0.11
     independence
    0.10
    Activations Density 0.013%

    No Known Activations