© 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. 9-LLAMASCOPE-RES-131K
    11. 98651
    Prev
    Next
    INDEX
    Explanations

    product specifications and ratings

    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
    orts
    -0.07
    ladu
    -0.06
     pur
    -0.05
     strut
    -0.05
    _SCOPE
    -0.05
     Kemp
    -0.05
     caution
    -0.05
     sparing
    -0.05
    ometric
    -0.05
    lug
    -0.05
    POSITIVE LOGITS
    åIJ¾
    0.07
     знаком
    0.07
    ÑĪÑĤов
    0.07
    ewise
    0.07
    kers
    0.07
    eum
    0.06
    edback
    0.06
    ums
    0.06
    ovky
    0.06
    ustain
    0.06
    Activations Density 0.008%

    No Known Activations