© 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. 119293
    Prev
    Next
    INDEX
    Explanations

    references to financial values and transactions

    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
    ril
    -0.07
    \base
    -0.07
    303
    -0.06
    оби
    -0.06
    Ħ件
    -0.06
    нож
    -0.06
    llen
    -0.06
    adu
    -0.06
    owl
    -0.06
    alf
    -0.06
    POSITIVE LOGITS
     beyond
    0.10
     greater
    0.09
     less
    0.09
    anything
    0.09
     below
    0.09
    eyond
    0.08
     além
    0.08
     above
    0.08
     anything
    0.08
     BELOW
    0.07
    Activations Density 0.050%

    No Known Activations