© 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. 75828
    Prev
    Next
    INDEX
    Explanations

    references to functions and methods related to object or data manipulation in programming

    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
    iones
    -0.07
    eydi
    -0.06
    ieux
    -0.06
    HasBeenSet
    -0.06
    isas
    -0.06
    macen
    -0.06
     Fle
    -0.06
     roma
    -0.06
    ï½Ń
    -0.06
    izard
    -0.06
    POSITIVE LOGITS
    ()
    0.09
    ().
    0.08
    (true
    0.08
    ()[
    0.07
     true
    0.07
    ()↵
    0.07
    449
    0.07
    ().↵
    0.07
    439
    0.07
    ())
    0.07
    Activations Density 0.068%

    No Known Activations