© 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. 73641
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions, involvement, and acknowledgment in 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
     also
    -0.07
     often
    -0.07
     just
    -0.06
    nul
    -0.06
    isque
    -0.06
     reverse
    -0.06
     perfect
    -0.06
     thereby
    -0.06
     equally
    -0.06
    .ins
    -0.06
    POSITIVE LOGITS
     SOME
    0.11
     somewhere
    0.11
     definitely
    0.10
    èĤ¯å®ļ
    0.09
     Definitely
    0.09
     indeed
    0.09
     kesinlikle
    0.09
     ÙĪØ£ÙĨ
    0.09
     irgend
    0.09
    åŃĺåľ¨
    0.09
    Activations Density 0.041%

    No Known Activations