© 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. 15397
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming functions and error handling

    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
     ear
    -0.06
     living
    -0.06
    ossa
    -0.06
     opinion
    -0.06
    olut
    -0.06
    ptr
    -0.06
     Stanton
    -0.06
     spinning
    -0.06
     Ear
    -0.06
     spin
    -0.05
    POSITIVE LOGITS
    Argument
    0.10
     argument
    0.09
     Argument
    0.09
     iParam
    0.09
     arg
    0.09
     arguments
    0.08
     getArguments
    0.08
    .Argument
    0.08
    argument
    0.08
    åĤ³
    0.08
    Activations Density 0.049%

    No Known Activations