© 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. 15-LLAMASCOPE-RES-131K
    11. 27511
    Prev
    Next
    INDEX
    Explanations

    references to organized support systems and associated social structures related to recovery and well-being

    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
    вад
    -0.07
    .scalablytyped
    -0.07
    ovice
    -0.07
    667
    -0.06
     Trojan
    -0.06
    stry
    -0.06
     actionTypes
    -0.06
    поÑĢ
    -0.06
    holm
    -0.06
     ÑĥÑģл
    -0.06
    POSITIVE LOGITS
     various
    0.11
     Various
    0.09
     numerous
    0.09
     several
    0.08
     countless
    0.08
    Various
    0.08
    åIJĦç§į
    0.07
     such
    0.07
    abile
    0.07
     assorted
    0.07
    Activations Density 0.052%

    No Known Activations