© 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. 16547
    Prev
    Next
    INDEX
    Explanations

    references to obligations, requirements, and procedural mandates

    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
    acam
    -0.08
    æĴ
    -0.07
    ikat
    -0.07
    ávÄĽ
    -0.07
    ettel
    -0.06
    λλη
    -0.06
     mac
    -0.06
    azed
    -0.06
    chor
    -0.06
    cname
    -0.06
    POSITIVE LOGITS
     reasons
    0.09
     Reasons
    0.07
    reason
    0.07
     accompanied
    0.07
     accompanies
    0.07
     explain
    0.07
     min
    0.07
     reason
    0.07
     explanation
    0.07
     accompany
    0.07
    Activations Density 0.017%

    No Known Activations