© 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 EvalsExportsAPI 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. 77106
    Prev
    Next
    INDEX
    Explanations

    references to probiotics and their benefits

    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
     "
    -0.06
    oui
    -0.06
     Wholesale
    -0.06
     inventory
    -0.06
     pre
    -0.06
    rought
    -0.05
     dropping
    -0.05
    420
    -0.05
     Unicorn
    -0.05
     '
    -0.05
    POSITIVE LOGITS
    Ìģt
    0.08
     rencont
    0.08
    .Invariant
    0.07
    سÙħØ©
    0.07
    forcer
    0.07
     mơ
    0.07
    ozÃŃ
    0.07
    yaw
    0.07
    ạch
    0.07
    ìĶ
    0.07
    Activations Density 0.003%

    No Known Activations