© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104191
    Prev
    Next
    INDEX
    Explanations

    references to the United Nations Security Council and its resolutions

    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
    swick
    -0.06
    emmel
    -0.06
    ìłĢ
    -0.06
     union
    -0.06
    æ£ļ
    -0.05
    APON
    -0.05
     shaft
    -0.05
    Verdana
    -0.05
     Haut
    -0.05
     Pend
    -0.05
    POSITIVE LOGITS
    arth
    0.07
    ycle
    0.07
     dashes
    0.07
    umba
    0.07
    Universal
    0.06
     UNS
    0.06
     esl
    0.06
     ((!
    0.06
    itespace
    0.06
     intl
    0.06
    Activations Density 0.002%

    No Known Activations