© 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. 15163
    Prev
    Next
    INDEX
    Explanations

    references to manufacturers and engineering companies, particularly in India

    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
    pear
    -0.07
    adir
    -0.07
    qa
    -0.07
    oui
    -0.07
    (GLFW
    -0.07
    uch
    -0.07
    ibri
    -0.07
    quam
    -0.07
    anno
    -0.07
    andas
    -0.06
    POSITIVE LOGITS
     near
    0.07
    /provider
    0.07
     Near
    0.06
     &
    0.06
    strstr
    0.06
     hem
    0.06
    614
    0.06
    ÑĪа
    0.06
    /operator
    0.06
    rica
    0.05
    Activations Density 0.004%

    No Known Activations