© 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. 79852
    Prev
    Next
    INDEX
    Explanations

    references to guidelines or instructions related to processes

    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
    elman
    -0.06
     besten
    -0.06
    åIJ§
    -0.06
     automatically
    -0.06
     uns
    -0.06
     Danh
    -0.06
     maybe
    -0.06
     red
    -0.06
     direct
    -0.06
     r
    -0.05
    POSITIVE LOGITS
     accurately
    0.09
     accurate
    0.08
    ransition
    0.08
    æŃ£ç¡®
    0.08
    accur
    0.08
    proper
    0.08
     بداÙĨ
    0.08
    655
    0.07
     correctly
    0.07
     olab
    0.07
    Activations Density 0.031%

    No Known Activations