© 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. 40747
    Prev
    Next
    INDEX
    Explanations

    references to weather conditions and uncertainties

    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
    ivery
    -0.07
    erer
    -0.07
    icle
    -0.07
    metro
    -0.07
    عÙĦ
    -0.06
    ÄįnÃŃk
    -0.06
    opak
    -0.06
    pery
    -0.06
    IGIN
    -0.06
     Volk
    -0.06
    POSITIVE LOGITS
     conv
    0.07
    ÙĪÙħات
    0.07
     Tropical
    0.07
    352
    0.07
    oma
    0.06
    ÐŁÐļ
    0.06
     Ling
    0.06
     coil
    0.06
     Coil
    0.06
    pez
    0.06
    Activations Density 0.001%

    No Known Activations