© 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. 69656
    Prev
    Next
    INDEX
    Explanations

    financial metrics related to stock prices and market values

    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
    yth
    -0.09
    igar
    -0.08
    erez
    -0.08
    aversable
    -0.07
    xes
    -0.07
    iciar
    -0.07
     interfer
    -0.06
    jerne
    -0.06
    ulen
    -0.06
    横
    -0.06
    POSITIVE LOGITS
    croft
    0.06
    cy
    0.06
     Fully
    0.06
    aping
    0.05
     driven
    0.05
     Strat
    0.05
    ÏĮÏĤ
    0.05
    TPL
    0.05
    FetchRequest
    0.05
    ele
    0.05
    Activations Density 0.007%

    No Known Activations