© 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. 40594
    Prev
    Next
    INDEX
    Explanations

    clauses and phrases that indicate conditions or exceptions

    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
    iglia
    -0.07
    ooks
    -0.06
    iena
    -0.06
     Herc
    -0.06
    ileo
    -0.06
    utzer
    -0.06
    ypad
    -0.06
    że
    -0.06
     bý
    -0.06
    lah
    -0.05
    POSITIVE LOGITS
    udos
    0.07
    à¸Ńà¸ģà¸Īาà¸ģà¸Ļ
    0.07
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.07
    istrovstvÃŃ
    0.06
    گاب
    0.06
    Gro
    0.06
    âĢ¦↵↵↵
    0.06
     Poz
    0.06
    jan
    0.06
    jez
    0.06
    Activations Density 0.377%

    No Known Activations