© 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. 84477
    Prev
    Next
    INDEX
    Explanations

    references to numeric data or quantities

    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
    robat
    -0.07
    hoff
    -0.06
    ensity
    -0.06
    .jsp
    -0.06
     å¹
    -0.06
    _AG
    -0.06
    кÑĥлÑĮ
    -0.06
    .GUI
    -0.06
     isp
    -0.06
    à¤ĺ
    -0.06
    POSITIVE LOGITS
     total
    0.13
    total
    0.10
     overall
    0.10
    Total
    0.09
     Total
    0.09
    _total
    0.09
     toplam
    0.09
    -total
    0.08
     TOTAL
    0.08
    .total
    0.08
    Activations Density 0.023%

    No Known Activations