© 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. 15413
    Prev
    Next
    INDEX
    Explanations

    numerals and monetary values related to financial transactions or 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
    clud
    -0.06
     Rew
    -0.06
    åĢĴ
    -0.06
    ãĤ¤ãĤ¹
    -0.05
    crew
    -0.05
     Millenn
    -0.05
     footing
    -0.05
     rates
    -0.05
    ay
    -0.05
    åıĤçħ§
    -0.05
    POSITIVE LOGITS
    μοÏģ
    0.08
    (æ°´
    0.07
    ahi
    0.07
    Ñİн
    0.07
    ationToken
    0.07
    ieri
    0.07
    ofi
    0.07
    eph
    0.07
     additional
    0.06
    .ga
    0.06
    Activations Density 0.019%

    No Known Activations