© 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. 54944
    Prev
    Next
    INDEX
    Explanations

    technical terms related to cybersecurity and network protocols

    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
     finally
    -0.08
    adel
    -0.07
    hof
    -0.07
     Finally
    -0.07
    Lastly
    -0.07
    .scalablytyped
    -0.06
    εÏĦ
    -0.06
    	finally
    -0.06
    elves
    -0.06
    adian
    -0.06
    POSITIVE LOGITS
    /or
    0.08
     Secondly
    0.07
    'gc
    0.06
    éĥİ
    0.06
    .Second
    0.06
    /of
    0.06
     ...↵↵
    0.06
    âĹĭ
    0.06
    esel
    0.06
     pimp
    0.06
    Activations Density 0.084%

    No Known Activations