© 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. 56263
    Prev
    Next
    INDEX
    Explanations

    statements about the importance of foundational principles or quality

    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
    uja
    -0.08
    uga
    -0.07
    ulan
    -0.07
    ToProps
    -0.07
    hani
    -0.07
    imbledon
    -0.07
    ascus
    -0.07
    ÙĪØ«
    -0.07
    Ñĥж
    -0.07
     dut
    -0.07
    POSITIVE LOGITS
     therefore
    0.10
     vice
    0.09
     Therefore
    0.08
    Therefore
    0.07
    ane
    0.07
     donc
    0.07
    ï¼ĮæīĢ以
    0.07
    ox
    0.07
     ucwords
    0.06
     Vice
    0.06
    Activations Density 0.082%

    No Known Activations