© 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. 79309
    Prev
    Next
    INDEX
    Explanations

    statements regarding changes or improvements

    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
    swire
    -0.07
    ,eg
    -0.07
    anan
    -0.07
    ycastle
    -0.07
    .dispatchEvent
    -0.07
    ÑĬ
    -0.07
     Jew
    -0.07
    ÄĽr
    -0.07
    iky
    -0.07
    orca
    -0.07
    POSITIVE LOGITS
     iar
    0.12
     while
    0.10
    while
    0.08
     whereas
    0.08
     And
    0.07
     there
    0.07
    hra
    0.07
     mentre
    0.07
    ï¼ĮèĢĮ
    0.07
     whilst
    0.07
    Activations Density 0.063%

    No Known Activations