© 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. 104515
    Prev
    Next
    INDEX
    Explanations

    phrases related to restrictions and exclusions in studies or processes

    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
     INCIDENT
    -0.07
     Incident
    -0.07
    maz
    -0.07
    favicon
    -0.06
    kl
    -0.06
    ault
    -0.06
     inev
    -0.06
    ÏĦÏħ
    -0.06
    _hop
    -0.06
     Yorker
    -0.05
    POSITIVE LOGITS
     ëķĮ문
    0.08
     too
    0.08
     Too
    0.08
    δα
    0.08
     lack
    0.08
    (reason
    0.07
     reasoned
    0.07
    æĮ¯
    0.07
    Too
    0.07
     TOO
    0.07
    Activations Density 0.022%

    No Known Activations