© 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. 22-LLAMASCOPE-RES-131K
    11. 3971
    Prev
    Next
    INDEX
    Explanations

    terms related to vegetation and plant life

    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
    zig
    -0.07
    گرد
    -0.07
    hole
    -0.06
    çļĦäºĭæĥħ
    -0.06
     lá»ĩ
    -0.06
    ç©´
    -0.06
    tail
    -0.06
    fect
    -0.06
     aday
    -0.06
    stones
    -0.06
    POSITIVE LOGITS
     growth
    0.10
    èĮĤ
    0.09
    ations
    0.09
     cover
    0.09
    -covered
    0.08
    growth
    0.08
    belt
    0.08
     coverage
    0.08
    rowth
    0.08
     growing
    0.08
    Activations Density 0.006%

    No Known Activations