© 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. 126478
    Prev
    Next
    INDEX
    Explanations

    terms related to server connectivity and operation

    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
     oku
    -0.07
     Shuttle
    -0.07
    luv
    -0.06
    eyn
    -0.06
     Ãĸr
    -0.06
    uraa
    -0.06
    á»Ĺ
    -0.06
     Stall
    -0.06
     обÑĢаÑī
    -0.06
    oled
    -0.06
    POSITIVE LOGITS
     server
    0.08
     party
    0.08
     game
    0.07
    server
    0.07
     formation
    0.07
    alse
    0.07
     join
    0.07
     participants
    0.07
    sez
    0.07
     Formation
    0.07
    Activations Density 0.012%

    No Known Activations