© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29953
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific timelines related to significant events or statistics

    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
    áj
    -0.06
    during
    -0.06
     fus
    -0.06
    éĴ
    -0.06
    reed
    -0.06
    was
    -0.06
    pus
    -0.06
     during
    -0.06
    erah
    -0.06
    äºİ
    -0.06
    POSITIVE LOGITS
     inception
    0.07
    rosso
    0.07
    Å¡Å¥
    0.07
    .scalablytyped
    0.07
    643
    0.07
    ignon
    0.06
     since
    0.06
     ince
    0.06
    lington
    0.06
    ÅĻez
    0.06
    Activations Density 0.020%

    No Known Activations