© 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. 78430
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to business metrics and performance

    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
    209
    -0.07
    ulin
    -0.07
    verse
    -0.06
    stro
    -0.06
    oin
    -0.06
    heet
    -0.06
    uteur
    -0.06
    313
    -0.06
    illions
    -0.06
    istles
    -0.06
    POSITIVE LOGITS
    atas
    0.08
    oleÄį
    0.07
    nonce
    0.07
    ãĤ¤ãĤ¹
    0.07
     false
    0.07
     Whereas
    0.07
     whereas
    0.06
    owitz
    0.06
     misc
    0.06
    rom
    0.06
    Activations Density 0.011%

    No Known Activations