© 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. 15101
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate speech or exclamations

    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
     titled
    -0.07
    Cum
    -0.07
     Hlav
    -0.07
    UND
    -0.06
    abay
    -0.06
    ÙħÙĪÙĦ
    -0.06
    agh
    -0.06
    ourg
    -0.06
     Cum
    -0.06
    agog
    -0.06
    POSITIVE LOGITS
     followed
    0.08
    ibel
    0.07
    ãĥ¼ãĤº
    0.06
    ä½
    0.06
    .newBuilder
    0.06
     etc
    0.06
    ť
    0.06
     pÅĻiÄįemž
    0.06
    RAINT
    0.06
    ailable
    0.06
    Activations Density 0.021%

    No Known Activations