© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 70504
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and database concepts

    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
     folks
    -0.09
     Fol
    -0.07
    ame
    -0.06
     firm
    -0.06
     interim
    -0.06
     &
    -0.06
     latest
    -0.06
     country
    -0.06
    aben
    -0.06
     spell
    -0.06
    POSITIVE LOGITS
    erce
    0.07
     addCriterion
    0.07
    .generated
    0.07
    antz
    0.07
    isContained
    0.07
     ê²ĮìĭľíĮIJ
    0.07
     activeClassName
    0.07
    Ä±ÅŁtır
    0.07
     NONINFRINGEMENT
    0.07
    notated
    0.07
    Activations Density 0.000%

    No Known Activations