© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118947
    Prev
    Next
    INDEX
    Explanations

    mentions of the NT (Windows Network Technology) operating system versions

    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
    UpInside
    -0.08
    ¡
    -0.08
    sworth
    -0.07
    andest
    -0.07
    uger
    -0.07
    utto
    -0.07
    hk
    -0.07
    ança
    -0.07
    thood
    -0.07
    igt
    -0.07
    POSITIVE LOGITS
     Trem
    0.07
    0.07
     winding
    0.06
    amo
    0.06
    ti
    0.06
    ائج
    0.06
    uitive
    0.06
    ure
    0.06
    abee
    0.06
    RODUCTION
    0.06
    Activations Density 0.009%

    No Known Activations