© 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. 1913
    Prev
    Next
    INDEX
    Explanations

    instances of attributes and changes within structured data or programming contexts

    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
    ãĥ³ãĥIJ
    -0.07
    obierno
    -0.07
    ober
    -0.07
    Ä©
    -0.07
    izr
    -0.07
    _LED
    -0.07
     Binder
    -0.07
    _NPC
    -0.07
    	Copyright
    -0.07
    ãĤ¤ãĥī
    -0.07
    POSITIVE LOGITS
     added
    0.21
     addition
    0.21
     additions
    0.18
     Added
    0.16
     thêm
    0.16
     Addition
    0.16
     adds
    0.16
    added
    0.15
     ì¶Ķê°Ģ
    0.15
     additional
    0.15
    Activations Density 0.052%

    No Known Activations