© 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. 81177
    Prev
    Next
    INDEX
    Explanations

    references to local governance and community-related disputes

    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
     köln
    -0.06
    665
    -0.06
    å®Ĺ
    -0.06
     Romeo
    -0.06
    /doc
    -0.06
    å¤ľ
    -0.06
     pán
    -0.06
     minHeight
    -0.06
    clr
    -0.06
    908
    -0.05
    POSITIVE LOGITS
    yms
    0.07
     Station
    0.07
     dil
    0.07
    ebek
    0.07
     ëĭ¤ìļ´ë°Ľê¸°
    0.07
     Eb
    0.07
    opsis
    0.07
     Castle
    0.07
     Memorial
    0.07
     Mill
    0.07
    Activations Density 0.340%

    No Known Activations