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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61600
    Prev
    Next
    INDEX
    Explanations

    first-person perspectives and personal experiences

    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
    avax
    -0.08
    upid
    -0.08
     Replies
    -0.07
    loo
    -0.07
    egas
    -0.07
    isoft
    -0.07
    ami
    -0.07
     Worth
    -0.07
     Dann
    -0.07
    orda
    -0.07
    POSITIVE LOGITS
    -described
    0.09
     described
    0.09
     describe
    0.08
     describes
    0.07
     mentioned
    0.07
     mention
    0.07
    æıIJ
    0.07
     description
    0.07
     proposal
    0.06
     sound
    0.06
    Activations Density 0.024%

    No Known Activations