© 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. 16158
    Prev
    Next
    INDEX
    Explanations

    keywords related to gaming and software, particularly installations and 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
    ↵
    -0.07
    :
    -0.06
    -0.05
     ↵
    -0.05
     relative
    -0.05
     "
    -0.05
    pon
    -0.05
     Loch
    -0.05
     =
    -0.05
     Victorian
    -0.05
    POSITIVE LOGITS
    setProperty
    0.08
     Yardım
    0.08
    isko
    0.08
     Nasıl
    0.08
    .LOG
    0.07
    .rar
    0.07
    大åħ¨
    0.07
    ardown
    0.07
    erli
    0.07
    аков
    0.07
    Activations Density 0.019%

    No Known Activations