© 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. 116813
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the provision of support services, especially in health-related 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
     createSelector
    -0.07
     Carrier
    -0.07
    erver
    -0.06
    аÑĢÑĩ
    -0.06
     ëĤ´ëł¤
    -0.06
    üml
    -0.06
    oose
    -0.06
    å¹¹ç·ļ
    -0.06
    .pub
    -0.06
     à¤ĩत
    -0.06
    POSITIVE LOGITS
     services
    0.10
     Debt
    0.08
     Services
    0.08
     fee
    0.07
    Services
    0.07
     ÑĥÑģлÑĥг
    0.07
     program
    0.07
     fees
    0.07
    ervices
    0.07
    fee
    0.07
    Activations Density 0.060%

    No Known Activations