© 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. 28380
    Prev
    Next
    INDEX
    Explanations

    references to names, titles, or entities

    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
    writeln
    -0.07
    ļĮ
    -0.07
    çĪ½
    -0.06
    гоÑĢ
    -0.06
    awning
    -0.06
    epar
    -0.06
     Duy
    -0.06
    .kr
    -0.06
    alta
    -0.06
    .beta
    -0.06
    POSITIVE LOGITS
    /no
    0.08
    -No
    0.08
    NO
    0.07
     apart
    0.07
    ,No
    0.07
    بÙĪ
    0.07
     кÑĢоме
    0.06
    No
    0.06
    -no
    0.06
     left
    0.06
    Activations Density 0.062%

    No Known Activations