© 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. 91959
    Prev
    Next
    INDEX
    Explanations

    references to discussions and community engagement, especially in the context of online interactions

    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
    _PHASE
    -0.07
    оÑĤÑĢеб
    -0.07
    mdl
    -0.07
     kles
    -0.07
    .kr
    -0.07
    ookie
    -0.06
    OLT
    -0.06
     mdl
    -0.06
    Ñĥй
    -0.06
    upertino
    -0.06
    POSITIVE LOGITS
     discussion
    0.10
     talk
    0.10
     discussions
    0.10
     Discussions
    0.09
     Topic
    0.09
     discuss
    0.09
     discussing
    0.09
     Talk
    0.09
     Discussion
    0.09
     topic
    0.09
    Activations Density 0.010%

    No Known Activations