© 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. 1920
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to biology and experimentation

    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
    ogh
    -0.06
    جÛĮ
    -0.06
     podÃŃ
    -0.06
     polled
    -0.06
     Flower
    -0.06
    kategori
    -0.06
    orpion
    -0.06
    zas
    -0.06
    ocache
    -0.06
     Ferm
    -0.06
    POSITIVE LOGITS
    inge
    0.08
    ols
    0.07
    ancia
    0.07
     semi
    0.07
    riel
    0.06
    edy
    0.06
     tools
    0.06
    pora
    0.06
    omics
    0.06
    tools
    0.06
    Activations Density 0.022%

    No Known Activations