© 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. 81506
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest conditional or hypothetical scenarios

    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
    itoris
    -0.06
    gom
    -0.06
    hua
    -0.06
    unless
    -0.06
    hk
    -0.06
     ims
    -0.06
     unless
    -0.06
     onRequest
    -0.06
    roi
    -0.06
    imo
    -0.06
    POSITIVE LOGITS
    Rare
    0.07
    еÑĪÑĮ
    0.06
    RTL
    0.06
     rare
    0.06
    endif
    0.06
    ount
    0.06
    dül
    0.06
    icit
    0.06
    çļĦè¯Ŀ
    0.06
     Ment
    0.06
    Activations Density 0.008%

    No Known Activations