© 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 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. 130465
    Prev
    Next
    INDEX
    Explanations

    phrases indicating educational contexts or references

    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
    oba
    -0.09
    apolis
    -0.07
    xico
    -0.07
    qd
    -0.07
    oki
    -0.06
    oci
    -0.06
    pis
    -0.06
    jabi
    -0.06
    .Selenium
    -0.06
    ãĥ¬ãĤ¤
    -0.06
    POSITIVE LOGITS
     subjects
    0.08
     topics
    0.08
    koa
    0.07
    ccount
    0.07
     Subjects
    0.06
    subjects
    0.06
     matters
    0.06
    idge
    0.06
     Egg
    0.06
    uckles
    0.06
    Activations Density 0.038%

    No Known Activations