© 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. 81424
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistics or data in a business 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
    ille
    -0.08
    åħ¸
    -0.07
     dime
    -0.06
    OTOR
    -0.06
    ervers
    -0.06
    ults
    -0.06
    apl
    -0.06
    É
    -0.06
     commons
    -0.06
    vang
    -0.06
    POSITIVE LOGITS
    /unit
    0.07
    erli
    0.07
     kr
    0.07
    BarButton
    0.06
    ertiary
    0.06
    YPE
    0.06
    ationToken
    0.06
     proje
    0.06
    erty
    0.06
    .locals
    0.06
    Activations Density 0.003%

    No Known Activations