© 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. 78939
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets, particularly involving nested structures and delimiters

    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
    {%
    -0.07
    ä¸ĢåĮº
    -0.07
     tslint
    -0.07
    acia
    -0.07
    oldem
    -0.07
    matic
    -0.07
    stad
    -0.07
    {{
    -0.07
    gy
    -0.07
    ange
    -0.07
    POSITIVE LOGITS
    adera
    0.08
    ;}
    0.06
    ucci
    0.06
    akin
    0.06
     little
    0.06
     Zem
    0.06
     Rudy
    0.06
    utin
    0.06
    abela
    0.06
    ìĦł
    0.06
    Activations Density 0.629%

    No Known Activations