© 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. 4839
    Prev
    Next
    INDEX
    Explanations

    concepts related to collaboration and shared effort

    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
     safest
    -0.09
    .googleapis
    -0.07
     безопаÑģ
    -0.07
    ledged
    -0.06
    bsp
    -0.06
     safer
    -0.06
    GLE
    -0.06
    etsk
    -0.06
    gle
    -0.06
    ĽĦ
    -0.06
    POSITIVE LOGITS
     properly
    0.12
    proper
    0.11
     proper
    0.11
     Proper
    0.10
     correctly
    0.09
     пÑĢавилÑĮно
    0.08
    care
    0.08
     richtig
    0.07
    æŃ£ç¡®
    0.07
     correct
    0.07
    Activations Density 0.063%

    No Known Activations