© 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 EvalsExportsinterp-engineNEWAPI 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. 54163
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity and influence in the context of markets and businesses

    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
    æ®Ĭ
    -0.07
    æģ
    -0.07
     Milf
    -0.07
    andard
    -0.07
    สาร
    -0.06
    zÄħd
    -0.06
     FETCH
    -0.06
    é½IJ
    -0.06
    ÑĪов
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
     potentially
    0.07
     sheer
    0.07
     count
    0.06
     size
    0.06
    lot
    0.06
     chances
    0.06
    retty
    0.06
     haystack
    0.06
     Stat
    0.06
     proportion
    0.06
    Activations Density 0.039%

    No Known Activations