© 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. 39736
    Prev
    Next
    INDEX
    Explanations

    nested structures and elements indicative of programming or markup syntax

    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
    loff
    -0.08
    atti
    -0.08
    \<^
    -0.07
     JsonRequestBehavior
    -0.07
    chaft
    -0.07
    å±
    -0.07
    ä¸ģ
    -0.07
    INCLUDED
    -0.07
    erde
    -0.07
    Č↵
    -0.07
    POSITIVE LOGITS
     third
    0.06
     conc
    0.06
    .EventArgs
    0.06
     array
    0.05
     (
    0.05
     A
    0.05
    jar
    0.05
     striped
    0.05
    3
    0.05
     Nev
    0.05
    Activations Density 0.009%

    No Known Activations