© 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. 83619
    Prev
    Next
    INDEX
    Explanations

    governmental and regulatory terms related to health and safety

    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
    vox
    -0.06
     Ink
    -0.06
     sub
    -0.06
    ero
    -0.06
    isl
    -0.06
     Bullet
    -0.05
    hest
    -0.05
    okes
    -0.05
    iska
    -0.05
    ost
    -0.05
    POSITIVE LOGITS
    arshal
    0.08
    (æ°´
    0.08
    utomation
    0.08
    arResult
    0.08
    imir
    0.08
    \a
    0.07
    *******************************************************************************/↵
    0.07
    utschen
    0.07
    chwitz
    0.07
    oogle
    0.07
    Activations Density 0.082%

    No Known Activations