© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    textual organization elements, such as headings and section formats

    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
    ãĥ³ãĥĸ
    -0.08
    #ad
    -0.06
     XC
    -0.06
    bei
    -0.06
    ISCO
    -0.06
     Tray
    -0.06
    orthand
    -0.06
    dej
    -0.06
    égor
    -0.06
    غاÙĦ
    -0.06
    POSITIVE LOGITS
     chapter
    0.08
     toc
    0.07
    toc
    0.07
     Heading
    0.07
     head
    0.07
    -indent
    0.07
    gregation
    0.07
    ÄįnÃŃk
    0.07
     headings
    0.07
     break
    0.07
    Activations Density 0.036%

    No Known Activations