© 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 EvalsExportsAPI 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. 126518
    Prev
    Next
    INDEX
    Explanations

    terms indicating deep significance or importance

    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
    ADE
    -0.08
    TING
    -0.07
    term
    -0.07
    DOG
    -0.07
    tings
    -0.07
    asso
    -0.07
    LEAN
    -0.07
    850
    -0.06
    BOARD
    -0.06
     stray
    -0.06
    POSITIVE LOGITS
    ly
    0.09
     depths
    0.09
    /ext
    0.08
    antly
    0.07
     deeply
    0.07
    ÑģÑĮ
    0.07
    ively
    0.07
     Depths
    0.07
    est
    0.07
    ément
    0.07
    Activations Density 0.002%

    No Known Activations