© 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. 78985
    Prev
    Next
    INDEX
    Explanations

    phrases that express conditional or explanatory relationships

    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
    kaar
    -0.09
    eração
    -0.08
    \Php
    -0.08
    dsl
    -0.07
    iques
    -0.07
    ä¸ĭ载次æķ°
    -0.07
    uch
    -0.07
    ême
    -0.07
    _plugins
    -0.07
    è³Ģ
    -0.07
    POSITIVE LOGITS
     once
    0.08
     instead
    0.07
    orgia
    0.07
     means
    0.07
     while
    0.07
     it
    0.07
     you
    0.06
     meaning
    0.06
     rather
    0.06
     While
    0.06
    Activations Density 0.021%

    No Known Activations