© 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. 108328
    Prev
    Next
    INDEX
    Explanations

    function definitions in code snippets

    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
    uchar
    -0.06
     Mayer
    -0.06
    olk
    -0.06
     int
    -0.06
     Magn
    -0.05
     Shields
    -0.05
     head
    -0.05
     Peterson
    -0.05
     professional
    -0.05
     friend
    -0.05
    POSITIVE LOGITS
     def
    0.11
    	def
    0.08
    braco
    0.08
    abstractmethod
    0.08
    ubber
    0.07
    anda
    0.07
    .prototype
    0.07
    istrovstvÃŃ
    0.07
    ()(
    0.07
    ToFront
    0.07
    Activations Density 0.008%

    No Known Activations