© 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. 61525
    Prev
    Next
    INDEX
    Explanations

    terms related to pathology and histological analysis

    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
    Ñıв
    -0.06
    ugins
    -0.06
    Nation
    -0.06
    ieres
    -0.06
    enberg
    -0.06
    гал
    -0.06
     fiss
    -0.06
    acons
    -0.06
    .eulerAngles
    -0.05
    .chomp
    -0.05
    POSITIVE LOGITS
     cell
    0.08
     histo
    0.08
     pathological
    0.07
     cellular
    0.07
     Robbins
    0.07
    hist
    0.07
    Ïģιο
    0.07
     electron
    0.07
     microscopic
    0.07
     hist
    0.07
    Activations Density 0.105%

    No Known Activations