© 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. 28026
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and functions in programming

    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
    SKTOP
    -0.07
    afen
    -0.06
    bat
    -0.06
    urf
    -0.06
    obel
    -0.06
    PPER
    -0.06
    nout
    -0.06
    Bat
    -0.06
     Bat
    -0.06
    оÑĤÑĢеб
    -0.06
    POSITIVE LOGITS
    Copying
    0.09
     æº
    0.09
     another
    0.08
    another
    0.08
     copying
    0.08
     source
    0.08
    .copy
    0.08
    ,copy
    0.08
     copy
    0.08
     Transfer
    0.08
    Activations Density 0.012%

    No Known Activations