© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59841
    Prev
    Next
    INDEX
    Explanations

    terms related to caffeinated beverages and health

    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
     mau
    -0.06
    sto
    -0.06
     Pon
    -0.05
     antig
    -0.05
    als
    -0.05
    alla
    -0.05
    nam
    -0.05
    eric
    -0.05
     Natur
    -0.05
    çļ
    -0.05
    POSITIVE LOGITS
     everything
    0.08
     Everything
    0.08
     versions
    0.07
    everything
    0.07
     VERSION
    0.07
    ëŀĢ
    0.07
     anything
    0.07
    addir
    0.07
    cies
    0.07
    æ¾
    0.07
    Activations Density 0.043%

    No Known Activations