© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    references to costs and expenses in various contexts

    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
    ucer
    -0.06
    å¥
    -0.06
     note
    -0.06
     Recycling
    -0.06
    wand
    -0.06
     earm
    -0.06
    chine
    -0.06
     regards
    -0.05
     Circle
    -0.05
    109
    -0.05
    POSITIVE LOGITS
    Truthy
    0.08
    ellig
    0.07
    ì£
    0.07
    ertia
    0.07
    Blank
    0.07
     tickets
    0.07
    endale
    0.07
     postage
    0.07
    Sharper
    0.07
    zew
    0.07
    Activations Density 0.016%

    No Known Activations