© 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. 17-LLAMASCOPE-RES-131K
    11. 16814
    Prev
    Next
    INDEX
    Explanations

    references to business transactions and investments

    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
    ÙħÛĮر
    -0.07
    evin
    -0.07
    รà¸ĵ
    -0.06
    éĽ²
    -0.06
    .Italic
    -0.06
    ÏĥÏĦαÏĥη
    -0.06
    styl
    -0.06
    omi
    -0.06
    ưỡng
    -0.06
     Gür
    -0.06
    POSITIVE LOGITS
    /***/
    0.07
    emen
    0.07
    ForRow
    0.07
     immediate
    0.07
     rank
    0.06
     Rack
    0.06
    itere
    0.06
     Timing
    0.06
    mdl
    0.06
     timing
    0.06
    Activations Density 0.007%

    No Known Activations