© 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. 17021
    Prev
    Next
    INDEX
    Explanations

    metrics related to financial calculations and comparisons in a business or academic context

    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
     nÃło
    -0.08
     ÑģооÑĤвеÑĤ
    -0.08
    ìĿ´ìĸ´
    -0.08
    OI
    -0.08
    abler
    -0.08
    beb
    -0.08
    alah
    -0.07
     yoksa
    -0.07
    ADF
    -0.07
    ((&
    -0.07
    POSITIVE LOGITS
     and
    0.25
     и
    0.19
     vÃł
    0.19
    and
    0.16
     ÈĻi
    0.16
     és
    0.16
    åĴĮ
    0.16
    	and
    0.15
     ë°ı
    0.15
     amd
    0.15
    Activations Density 5.311%

    No Known Activations