© 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. 15-LLAMASCOPE-RES-131K
    11. 86815
    Prev
    Next
    INDEX
    Explanations

    immersive experiences and perspectives in storytelling

    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
    ypy
    -0.07
    Æ°á»Ľng
    -0.06
     ÑģилÑĥ
    -0.06
    esty
    -0.06
    éł¼
    -0.06
    awi
    -0.06
    моÑĢ
    -0.06
    ãĥ³ãĤ¯
    -0.06
    ạp
    -0.06
    /scripts
    -0.06
    POSITIVE LOGITS
    823
    0.07
     directly
    0.07
     experience
    0.07
    dej
    0.06
    zym
    0.06
    ottie
    0.06
    \grid
    0.06
     experiencing
    0.06
    ivery
    0.06
    lej
    0.06
    Activations Density 0.013%

    No Known Activations