© 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. 87119
    Prev
    Next
    INDEX
    Explanations

    references to knowledge, technology applications, or training related to specific tasks and safety in work environments

    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
    UInteger
    -0.07
    eprom
    -0.07
    çļ
    -0.07
    ekil
    -0.07
    $MESS
    -0.07
    egers
    -0.07
    δÏĮν
    -0.07
     iParam
    -0.06
    ÑĨеÑģ
    -0.06
    pty
    -0.06
    POSITIVE LOGITS
    anda
    0.07
     actionTypes
    0.06
    (disposing
    0.05
    enis
    0.05
     pul
    0.05
    getAs
    0.05
    aceae
    0.05
     chaos
    0.05
    uga
    0.05
    enne
    0.05
    Activations Density 0.064%

    No Known Activations