© 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. 119597
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a contrast or comparison in context

    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
    ÑĥлÑı
    -0.08
    _Il
    -0.07
    òi
    -0.07
    еÑĤÑĥ
    -0.07
    ì¸
    -0.07
     getch
    -0.07
    alloca
    -0.07
    elog
    -0.07
    etal
    -0.07
    ãĤ´ãĥª
    -0.07
    POSITIVE LOGITS
     Bail
    0.06
     then
    0.06
    azu
    0.06
    andler
    0.06
     Jacob
    0.06
     Reb
    0.06
     Elm
    0.05
     wars
    0.05
     narr
    0.05
     Binder
    0.05
    Activations Density 0.219%

    No Known Activations