© 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. 70096
    Prev
    Next
    INDEX
    Explanations

    words indicating financial distress or viability issues

    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
    ovo
    -0.07
     Overall
    -0.07
     altogether
    -0.07
    iscal
    -0.06
     @}
    -0.06
     Lou
    -0.06
    quo
    -0.06
     hy
    -0.06
    é½
    -0.06
    Overall
    -0.06
    POSITIVE LOGITS
    opi
    0.07
    ضة
    0.07
    WithOptions
    0.07
    needle
    0.06
    ugin
    0.06
     اÙĦأد
    0.06
    aversable
    0.06
    urry
    0.06
    .LookAndFeel
    0.06
    ----------</
    0.06
    Activations Density 0.000%

    No Known Activations