© 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. 17-LLAMASCOPE-RES-131K
    11. 129412
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to data processing and manipulation

    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
    eric
    -0.06
    izzy
    -0.06
    UT
    -0.06
     Strat
    -0.06
    _extensions
    -0.06
    apur
    -0.05
    su
    -0.05
    sou
    -0.05
     Mer
    -0.05
    วà¸Ķ
    -0.05
    POSITIVE LOGITS
     else
    0.19
     otherwise
    0.17
     Otherwise
    0.15
    else
    0.15
    otherwise
    0.14
     ELSE
    0.14
    	else
    0.14
     Else
    0.14
    Otherwise
    0.14
    _else
    0.14
    Activations Density 0.013%

    No Known Activations