© 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. 69444
    Prev
    Next
    INDEX
    Explanations

    financial costs related to various subjects

    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
    kest
    -0.07
    awan
    -0.07
    çek
    -0.07
     Spending
    -0.07
    IOR
    -0.07
    lion
    -0.07
    Outlined
    -0.07
    thon
    -0.07
    ingham
    -0.07
     spending
    -0.06
    POSITIVE LOGITS
     dearly
    0.10
     blush
    0.06
    çĤ®
    0.06
     Lose
    0.06
     lost
    0.06
    loss
    0.06
     forfe
    0.06
    urret
    0.06
    ronic
    0.06
     Upgrade
    0.06
    Activations Density 0.008%

    No Known Activations