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

    Neuronpedia

    Jacobian LensNEW
    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. 119260
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions indicating comparisons or amounts

    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
    ÑģилÑĮ
    -0.08
    виÑĩ
    -0.07
    ãģĵãĤį
    -0.07
    ildiÄŁi
    -0.07
    ãĤ¤ãĥ¤
    -0.06
    raig
    -0.06
    евеÑĢ
    -0.06
    iêu
    -0.06
    ,↵↵↵↵
    -0.06
    __,__
    -0.06
    POSITIVE LOGITS
     dozen
    0.09
    ania
    0.07
    700
    0.06
     half
    0.06
     hundreds
    0.06
     MediaQuery
    0.06
    ajs
    0.06
    yonel
    0.06
    pheric
    0.06
    lane
    0.06
    Activations Density 0.034%

    No Known Activations