© 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. 84322
    Prev
    Next
    INDEX
    Explanations

    variables and mathematical expressions related to problem-solving in equations

    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
    elin
    -0.07
    uhn
    -0.07
    urgy
    -0.07
    oss
    -0.07
    rms
    -0.07
    ucz
    -0.06
    ooke
    -0.06
     Osw
    -0.06
    timezone
    -0.06
    urge
    -0.06
    POSITIVE LOGITS
     thereby
    0.08
    .
    0.07
     ÙĪØ°ÙĦÙĥ
    0.06
    ÃŃÅ¡
    0.06
    WARDED
    0.06
    ãĢĤãģĵãĤĮ
    0.06
    orex
    0.06
     afin
    0.06
     manners
    0.06
     while
    0.06
    Activations Density 0.006%

    No Known Activations