© 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. 42316
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and their backgrounds

    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
    rov
    -0.07
     Fold
    -0.07
    fold
    -0.07
    -fold
    -0.07
    reater
    -0.07
    413
    -0.07
    aras
    -0.06
    æķ£
    -0.06
    arih
    -0.06
    ohn
    -0.06
    POSITIVE LOGITS
     born
    0.11
    born
    0.08
    çĶŁ
    0.08
     çĶŁ
    0.08
     Born
    0.07
    -born
    0.07
     alive
    0.07
    Born
    0.07
    çĶŁçļĦ
    0.06
    ìĥĿ
    0.06
    Activations Density 0.060%

    No Known Activations