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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15447
    Prev
    Next
    INDEX
    Explanations

    statements regarding official permits and requests

    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
    slaught
    -0.08
    istrovstvÃŃ
    -0.08
    anzi
    -0.07
    erties
    -0.07
    odzi
    -0.07
    ãģĦãģĭ
    -0.07
     íݸ
    -0.07
    inha
    -0.07
    erti
    -0.07
    êµ´
    -0.07
    POSITIVE LOGITS
     supposed
    0.12
     previously
    0.09
     supposedly
    0.09
     already
    0.09
     earlier
    0.08
     recently
    0.08
     previous
    0.08
     meant
    0.07
     explicitly
    0.07
    ãģ¯ãģļ
    0.07
    Activations Density 0.025%

    No Known Activations