© 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. 27390
    Prev
    Next
    INDEX
    Explanations

    content related to gardening and landscaping activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common grammatical function words (prepositions, articles, conjunctions) that connect sentence elements in formal or technical writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    .↵↵↵↵↵↵↵↵
    -0.13
    .↵↵↵↵↵↵↵↵↵↵
    -0.12
    .DropDown
    -0.12
    .attachment
    -0.12
    !↵↵↵↵
    -0.12
     servis
    -0.12
     arac
    -0.11
    âĢ¦.↵↵
    -0.11
    .partial
    -0.11
    ,...↵↵
    -0.11
    POSITIVE LOGITS
    UpInside
    0.07
    bsites
    0.07
    0.07
    Âł
    0.07
     ostensibly
    0.07
     intimately
    0.07
     modest
    0.07
     (
    0.06
     ^{
    0.06
     immensely
    0.06
    Activations Density 71.196%

    No Known Activations