© 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. 130911
    Prev
    Next
    INDEX
    Explanations

    terms related to temperature and seasonal changes

    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
    PÅĻed
    -0.07
     dziew
    -0.07
    agal
    -0.07
    CurrentValue
    -0.07
    blr
    -0.07
    olet
    -0.07
    hv
    -0.07
     Jeho
    -0.07
    vsp
    -0.07
    اگ
    -0.07
    POSITIVE LOGITS
    ĤŃ
    0.06
    ekyll
    0.06
    äd
    0.06
     scheme
    0.06
    WebService
    0.06
    irm
    0.06
     herein
    0.05
     Martin
    0.05
     Tim
    0.05
     adj
    0.05
    Activations Density 0.001%

    No Known Activations