© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83365
    Prev
    Next
    INDEX
    Explanations

    references to structured data, documents, and formal training resources

    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
     İli
    -0.07
    liš
    -0.06
    ersiz
    -0.06
     صÙģ
    -0.06
    ãĥ³ãĥĶ
    -0.06
    ÏĥÏĢ
    -0.06
     zdrav
    -0.06
     ÙħÙĪÙĤع
    -0.06
    üç
    -0.06
    shiv
    -0.06
    POSITIVE LOGITS
     B
    0.17
    _B
    0.14
    .B
    0.13
    Âłb
    0.13
     Ðij
    0.13
    -B
    0.13
    _b
    0.13
    	B
    0.12
     b
    0.12
    ,B
    0.12
    Activations Density 0.740%

    No Known Activations