© 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. 5366
    Prev
    Next
    INDEX
    Explanations

    instances of events or occurrences related to community and public gatherings

    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
    缤
    -0.08
    (=)
    -0.07
    hydrate
    -0.07
    دÙĪد
    -0.07
    ืà¸Ńà¸Ļ
    -0.07
    .DOM
    -0.07
    _HAL
    -0.06
    تغ
    -0.06
    ãĥĨãĥ«
    -0.06
    urd
    -0.06
    POSITIVE LOGITS
     representatives
    0.07
     hierarchy
    0.07
     Vice
    0.07
     delegation
    0.06
    elen
    0.06
     President
    0.06
     members
    0.06
     vice
    0.06
     entire
    0.06
     culmination
    0.06
    Activations Density 0.074%

    No Known Activations