© 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. 29652
    Prev
    Next
    INDEX
    Explanations

    URLs and phrases related to software licenses

    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
    .scalablytyped
    -0.09
     sensit
    -0.07
    Äįer
    -0.06
    eny
    -0.06
    aris
    -0.06
    eldon
    -0.06
    unkt
    -0.06
    ition
    -0.06
    éŁ³
    -0.06
    ÙĤÙħ
    -0.06
    POSITIVE LOGITS
    ]={↵
    0.07
    iar
    0.06
    utos
    0.06
    ä¹ĭä¸Ģ
    0.06
    ieties
    0.06
     '>
    0.06
     indeb
    0.06
    kker
    0.06
     Dun
    0.06
    าะ
    0.06
    Activations Density 0.000%

    No Known Activations