© 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. 62421
    Prev
    Next
    INDEX
    Explanations

    terms related to historical context and literature

    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
    HEME
    -0.08
    ulos
    -0.07
    PLUS
    -0.07
    unma
    -0.07
    ignon
    -0.07
    avanaugh
    -0.06
     Drew
    -0.06
    etat
    -0.06
    §è¡Į
    -0.06
    ethereum
    -0.06
    POSITIVE LOGITS
    ertia
    0.06
     puzzles
    0.06
    LC
    0.06
    лини
    0.05
    oy
    0.05
    ida
    0.05
    Cong
    0.05
    æ²
    0.05
     éħ
    0.05
    æĢ§
    0.05
    Activations Density 0.001%

    No Known Activations