© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    significant opinions or critiques about novel ideas or works

    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
    vise
    -0.06
     persön
    -0.06
     SHALL
    -0.06
    _SR
    -0.06
     Gow
    -0.06
    isinden
    -0.06
    anno
    -0.06
     oma
    -0.05
    ç»Ŀ
    -0.05
    cu
    -0.05
    POSITIVE LOGITS
     merely
    0.12
     normal
    0.12
     ordinary
    0.10
     routine
    0.10
     nothing
    0.09
     mere
    0.09
     simply
    0.09
     simplement
    0.09
    normal
    0.09
     everyday
    0.09
    Activations Density 0.038%

    No Known Activations