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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95618
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms related to events and transactions

    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
     же
    -0.07
    hurst
    -0.07
     ours
    -0.07
    inho
    -0.06
    ãģ¨ãģĵãĤį
    -0.06
    arta
    -0.06
    afort
    -0.06
    createClass
    -0.06
     Organisation
    -0.06
    646
    -0.06
    POSITIVE LOGITS
    eman
    0.07
    uming
    0.06
    inke
    0.06
    erdale
    0.06
     offense
    0.06
    inker
    0.06
     coat
    0.06
    浩
    0.06
    ero
    0.06
    indir
    0.06
    Activations Density 0.048%

    No Known Activations