© 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. 15-LLAMASCOPE-RES-131K
    11. 90712
    Prev
    Next
    INDEX
    Explanations

    references to quantities or frequencies expressed per unit of measure

    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
    yard
    -0.08
    egg
    -0.08
    ebi
    -0.07
    imum
    -0.07
    ÑĨеÑĢ
    -0.07
    eki
    -0.07
    eg
    -0.07
    ek
    -0.07
    ãĥ¼ãĤ
    -0.07
    Äħ
    -0.07
    POSITIVE LOGITS
     annum
    0.09
    iphery
    0.07
     capita
    0.07
    missive
    0.07
    æѤ
    0.07
    quisites
    0.07
    elman
    0.06
    ween
    0.06
    ÑĢе
    0.06
    ipherals
    0.06
    Activations Density 0.018%

    No Known Activations