© 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. 72764
    Prev
    Next
    INDEX
    Explanations

    references to success, values, and principles in various contexts

    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
     (
    -0.06
     Din
    -0.06
    ÑĭÑģ
    -0.06
    INET
    -0.06
    λί
    -0.06
    å»
    -0.06
    uffers
    -0.06
    ĵåIJį
    -0.06
    oret
    -0.05
     Windsor
    -0.05
    POSITIVE LOGITS
    meyi
    0.08
    erner
    0.07
    ongyang
    0.07
    dzi
    0.07
     philosophy
    0.07
    atak
    0.07
     forIndexPath
    0.07
     approach
    0.07
    å²Ĺ
    0.07
    quan
    0.07
    Activations Density 0.031%

    No Known Activations