© 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. 2711
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing important moments or realizations

    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
    eb
    -0.07
     tem
    -0.06
    atcher
    -0.06
     sins
    -0.06
    opl
    -0.06
    ocator
    -0.06
    ért
    -0.05
    ãĤīãģĹãģĦ
    -0.05
     involved
    -0.05
    adero
    -0.05
    POSITIVE LOGITS
    ãģĵãģĿ
    0.08
    ledi
    0.07
    esiz
    0.07
    ipple
    0.07
    иÑģлов
    0.07
    âĢ¢↵↵
    0.07
    agas
    0.07
    ittal
    0.07
     experience
    0.07
    illy
    0.07
    Activations Density 0.037%

    No Known Activations