© 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. 123814
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or DOI references related to scientific articles

    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
    paren
    -0.06
    UNET
    -0.06
    utton
    -0.06
    DrawerToggle
    -0.06
    ÑĢÑİ
    -0.06
    aska
    -0.06
    eler
    -0.05
    iÄĻ
    -0.05
    uant
    -0.05
    duto
    -0.05
    POSITIVE LOGITS
    imitive
    0.07
    yna
    0.06
    .Board
    0.06
    è½½
    0.06
    ÄĽst
    0.06
    avaÅŁ
    0.06
    lamaz
    0.06
     Woj
    0.06
    ovy
    0.06
    fuse
    0.06
    Activations Density 0.003%

    No Known Activations