© 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. 39014
    Prev
    Next
    INDEX
    Explanations

    quantitative performance metrics related to financial data

    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
    uzzer
    -0.08
    otte
    -0.07
    ué
    -0.07
    enstvÃŃ
    -0.07
    ÑģоÑĤ
    -0.07
    ůsob
    -0.07
    jin
    -0.07
    ê´Ģ
    -0.07
     occas
    -0.07
    utenberg
    -0.07
    POSITIVE LOGITS
    us
    0.06
     Mus
    0.06
    ordon
    0.05
    htmlspecialchars
    0.05
    ornado
    0.05
     DispatchQueue
    0.05
     nop
    0.05
    inent
    0.05
    azu
    0.05
     Imperial
    0.05
    Activations Density 0.050%

    No Known Activations