© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to personal experiences and reflections on various topics

    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
     uk
    -0.08
    uk
    -0.08
     UK
    -0.08
     ‘
    -0.07
     London
    -0.07
    UK
    -0.07
     Britain
    -0.06
    London
    -0.06
     brit
    -0.06
    Iso
    -0.06
    POSITIVE LOGITS
     à¹Ĩ
    0.10
     theater
    0.09
    neighbor
    0.08
     harbor
    0.08
    _behavior
    0.08
    avior
    0.08
     canceled
    0.08
    ãģ»ãģĨ
    0.08
    Behavior
    0.08
     traveler
    0.08
    Activations Density 0.733%

    No Known Activations