© 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. 15-LLAMASCOPE-RES-131K
    11. 751
    Prev
    Next
    INDEX
    Explanations

    keywords related to media and articles

    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
    uye
    -0.08
    .springboot
    -0.07
    idge
    -0.06
    hl
    -0.06
     Herc
    -0.06
    roll
    -0.06
    iman
    -0.06
    é¡ĶãĤĴ
    -0.06
    èª
    -0.06
     ÙĨظرÛĮ
    -0.06
    POSITIVE LOGITS
    оÑĢаÑı
    0.07
    .Blocks
    0.07
    _FILENO
    0.06
    StateChanged
    0.06
    .ease
    0.06
     freely
    0.06
    lassen
    0.05
     transf
    0.05
    FORE
    0.05
     removeAll
    0.05
    Activations Density 0.061%

    No Known Activations