© 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. 81780
    Prev
    Next
    INDEX
    Explanations

    references to research and writing experiences related to historical events or personal reflections

    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
    ilingual
    -0.06
    licht
    -0.06
    upp
    -0.06
    à¹Ģà¸Ĺศ
    -0.06
    ICS
    -0.06
     witnessing
    -0.06
    ihan
    -0.06
    iral
    -0.05
     detect
    -0.05
     deutsch
    -0.05
    POSITIVE LOGITS
     research
    0.11
     Research
    0.09
    Research
    0.09
    research
    0.09
     sources
    0.09
     researching
    0.08
     researched
    0.08
     Sources
    0.08
     source
    0.07
    tsx
    0.07
    Activations Density 0.020%

    No Known Activations