© 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. 5-LLAMASCOPE-RES-131K
    11. 126796
    Prev
    Next
    INDEX
    Explanations

    references to ice 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
    elper
    -0.08
    اÙĬر
    -0.07
    нÑĮ
    -0.06
    EDIUM
    -0.06
    راÙģ
    -0.06
    LOGY
    -0.06
    .fn
    -0.06
     ç±
    -0.06
    ÑĥÑĢа
    -0.06
     Burton
    -0.06
    POSITIVE LOGITS
    express
    0.08
    untime
    0.07
    ec
    0.06
    conc
    0.06
    alar
    0.06
    osl
    0.06
    èĤ²
    0.06
    aren
    0.06
    rij
    0.06
    essional
    0.06
    Activations Density 0.001%

    No Known Activations