© 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. 55607
    Prev
    Next
    INDEX
    Explanations

    terms related to health, particularly studies involving lung health

    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
     ancor
    -0.07
    toi
    -0.07
     Mein
    -0.06
    panse
    -0.06
     zoekt
    -0.06
     tut
    -0.06
    alogy
    -0.06
    Äįná
    -0.06
    undi
    -0.06
    inh
    -0.06
    POSITIVE LOGITS
    -caret
    0.07
    CSR
    0.06
    adaÅŁ
    0.06
    λÏĮ
    0.06
    eson
    0.06
    /feed
    0.06
    modifiable
    0.06
    ÑĢев
    0.06
    rev
    0.06
    UNC
    0.06
    Activations Density 0.000%

    No Known Activations