© 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. 57401
    Prev
    Next
    INDEX
    Explanations

    operations related to data summarization and filtering in a programming context

    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
    amy
    -0.08
    astos
    -0.07
    _MAY
    -0.07
    بÙĪاسطة
    -0.07
    aze
    -0.06
    iran
    -0.06
    asto
    -0.06
    omy
    -0.06
     GFX
    -0.06
    çon
    -0.06
    POSITIVE LOGITS
    :
    0.07
    orsch
    0.07
    (↵
    0.07
    acey
    0.06
    ifi
    0.06
     rede
    0.06
    маз
    0.06
    orman
    0.06
    upp
    0.06
    :↵
    0.06
    Activations Density 0.042%

    No Known Activations