© 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. 106219
    Prev
    Next
    INDEX
    Explanations

    specific time or scheduling information related to operating hours

    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
    ë²Į
    -0.07
    ìŀĸ
    -0.07
    turnstile
    -0.07
    اتر
    -0.07
     strokeLine
    -0.07
     çİ
    -0.06
    .dtp
    -0.06
    istar
    -0.06
     flashback
    -0.06
    CurrentValue
    -0.06
    POSITIVE LOGITS
    .UnitTesting
    0.07
    olist
    0.06
     Bor
    0.06
     bor
    0.06
     shut
    0.06
    orus
    0.06
    -END
    0.06
     except
    0.05
    essaging
    0.05
    asure
    0.05
    Activations Density 0.005%

    No Known Activations