© 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. 26685
    Prev
    Next
    INDEX
    Explanations

    references to conditions or features relating to cold environments or ice-related terms

    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
    chten
    -0.07
     blo
    -0.07
    ï¸
    -0.06
     coinc
    -0.06
    elez
    -0.06
     staying
    -0.06
     Yates
    -0.06
     ÑģпÑĢава
    -0.06
     Entr
    -0.06
     wherever
    -0.06
    POSITIVE LOGITS
    holm
    0.08
     contexto
    0.07
    ToProps
    0.07
    eldom
    0.06
    nivel
    0.06
    328
    0.06
    ëĭĺìĿ´
    0.06
    .settings
    0.06
     contexts
    0.06
    -context
    0.06
    Activations Density 0.012%

    No Known Activations