© 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 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. 106539
    Prev
    Next
    INDEX
    Explanations

    significant quotes, revelations, and memorable moments related to impactful stories or events

    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
     synonyms
    -0.06
     notamment
    -0.06
    959
    -0.06
     Lyn
    -0.06
    loggedin
    -0.06
     Charm
    -0.06
    ecess
    -0.06
    quals
    -0.06
    ););↵
    -0.06
     Exists
    -0.06
    POSITIVE LOGITS
     came
    0.07
     belong
    0.07
    undler
    0.06
    conti
    0.06
     happened
    0.06
     occurs
    0.06
    yet
    0.06
     occurred
    0.06
     cor
    0.06
    undy
    0.06
    Activations Density 0.041%

    No Known Activations