© 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. 89342
    Prev
    Next
    INDEX
    Explanations

    interactions and requests for reviews or feedback

    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
    ÃĹ↵↵
    -0.07
    oola
    -0.06
    HELP
    -0.06
     Shank
    -0.06
     Forward
    -0.06
    Forward
    -0.06
     ÐĴики
    -0.06
    gressor
    -0.05
     Civic
    -0.05
    forward
    -0.05
    POSITIVE LOGITS
     köln
    0.08
     münchen
    0.07
    idis
    0.07
    ddf
    0.07
    outh
    0.07
    ни
    0.07
    iliar
    0.06
    eum
    0.06
    asan
    0.06
    orget
    0.06
    Activations Density 0.048%

    No Known Activations