© 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 EvalsExportsinterp-engineNEWAPI 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. 41691
    Prev
    Next
    INDEX
    Explanations

    key terms related to data transmission and networking applications

    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
    awe
    -0.07
     ('
    -0.07
    (Print
    -0.07
     McCart
    -0.07
    ascript
    -0.06
     Düz
    -0.06
    á»Ŀ
    -0.06
    stroy
    -0.06
    dbl
    -0.06
    peq
    -0.06
    POSITIVE LOGITS
    icha
    0.07
     kind
    0.07
    ela
    0.06
    liter
    0.06
    bot
    0.06
    ãĥ¼ãĥł
    0.06
    bas
    0.06
    oms
    0.06
     ++
    0.06
    cest
    0.06
    Activations Density 0.000%

    No Known Activations