© 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 EvalsExportsAPI 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. 85674
    Prev
    Next
    INDEX
    Explanations

    concepts related to control and regulation within various contexts

    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
    amp
    -0.07
    VD
    -0.07
     mez
    -0.06
    inas
    -0.06
     mine
    -0.06
     neighbor
    -0.06
    706
    -0.06
    iny
    -0.06
     hex
    -0.06
     unseren
    -0.06
    POSITIVE LOGITS
    該
    0.10
    该
    0.10
     particular
    0.10
     íķ´ëĭ¹
    0.09
    æŁIJ
    0.09
     said
    0.08
    htdocs
    0.07
     Darling
    0.07
     <",
    0.07
    undler
    0.07
    Activations Density 0.161%

    No Known Activations