© 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. 27767
    Prev
    Next
    INDEX
    Explanations

    conditional statements regarding financial situations and contract performance

    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
     cerv
    -0.07
    tej
    -0.06
    ç¨ĭ度
    -0.06
     Cougar
    -0.06
    existent
    -0.06
    ائد
    -0.06
    essian
    -0.06
     vulner
    -0.06
    pig
    -0.06
    vise
    -0.06
    POSITIVE LOGITS
     ultimately
    0.08
     ultimate
    0.07
     hypoth
    0.06
    ze
    0.06
     unchanged
    0.06
     somehow
    0.06
     fails
    0.06
    anova
    0.06
    ype
    0.06
    MLE
    0.06
    Activations Density 0.023%

    No Known Activations