© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107064
    Prev
    Next
    INDEX
    Explanations

    the concept of free or no-cost services and offerings

    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
    hardt
    -0.08
    ãĥ³ãĥĶ
    -0.07
     FactoryBot
    -0.07
    arde
    -0.07
    nej
    -0.07
    indr
    -0.06
    arp
    -0.06
    agh
    -0.06
     Ale
    -0.06
    /upload
    -0.06
    POSITIVE LOGITS
     press
    0.06
    -of
    0.06
     Conj
    0.06
    ivic
    0.06
    LAG
    0.06
     Punch
    0.06
     Excell
    0.06
    ständ
    0.05
     gratis
    0.05
     pitch
    0.05
    Activations Density 0.002%

    No Known Activations