© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27873
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and substances related to pharmaceuticals and toxicology

    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
    xin
    -0.06
     sẵn
    -0.06
     accept
    -0.06
    lum
    -0.05
    вÑģÑı
    -0.05
    estate
    -0.05
     Burnett
    -0.05
     fines
    -0.05
    etter
    -0.05
    465
    -0.05
    POSITIVE LOGITS
    ionage
    0.08
    keit
    0.08
    egra
    0.07
    alion
    0.07
    oteric
    0.07
    onia
    0.07
    lettes
    0.07
    styl
    0.07
    ibern
    0.07
    leta
    0.07
    Activations Density 0.035%

    No Known Activations