© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62210
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical medical studies and research

    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
    ÙĪÙĨÙĩ
    -0.09
     fitte
    -0.08
    .Accessible
    -0.08
    aben
    -0.08
    uze
    -0.08
    ewire
    -0.07
    .hardware
    -0.07
    ebek
    -0.07
    _FEATURE
    -0.07
    .uc
    -0.07
    POSITIVE LOGITS
     single
    0.06
    175
    0.06
    694
    0.06
    flo
    0.05
    fy
    0.05
    -c
    0.05
    acam
    0.05
    ↵
    0.05
    olo
    0.05
     brig
    0.05
    Activations Density 0.006%

    No Known Activations