© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77447
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific methodology and research studies

    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
    abet
    -0.06
    lich
    -0.06
     mechanical
    -0.05
    /slick
    -0.05
    ilot
    -0.05
    (IService
    -0.05
     fatalError
    -0.05
    UBL
    -0.05
    ibu
    -0.05
     Lit
    -0.05
    POSITIVE LOGITS
    æĺ¯ä¸ª
    0.10
    æĺ¯ä¸Ģ个
    0.10
    ype
    0.09
    à¹ģà¸ļà¸ļ
    0.09
     type
    0.09
     Type
    0.08
     typu
    0.08
    ç±»åŀĭ
    0.08
    Type
    0.08
     tipo
    0.08
    Activations Density 0.135%

    No Known Activations