© 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. 89343
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing and product specifications

    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
    ÂŃn
    -0.07
    otland
    -0.07
    наÑĤ
    -0.07
    inati
    -0.07
     çݩ家
    -0.07
    /Instruction
    -0.07
    æª
    -0.07
    át
    -0.07
    agedList
    -0.06
    天åłĤ
    -0.06
    POSITIVE LOGITS
     solutions
    0.06
     industrial
    0.06
     specialty
    0.06
    ite
    0.06
     OEM
    0.06
     anc
    0.06
     IT
    0.06
     medical
    0.06
     Industrial
    0.05
     enc
    0.05
    Activations Density 0.020%

    No Known Activations