© 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. 9-LLAMASCOPE-RES-131K
    11. 95149
    Prev
    Next
    INDEX
    Explanations

    specific terms associated with official documentation and literature

    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
    Trader
    -0.06
     Laur
    -0.06
    arrant
    -0.06
     bag
    -0.06
     -*-č↵
    -0.05
    orthand
    -0.05
     slash
    -0.05
     hurd
    -0.05
    rapid
    -0.05
     immortal
    -0.05
    POSITIVE LOGITS
     geil
    0.08
    /Gate
    0.08
    íķĺëĬĶëį°
    0.07
    Ðİ
    0.07
    onya
    0.07
    ØŃÙĦ
    0.07
     pÅĻÃŃležit
    0.07
     Roose
    0.07
    ặ
    0.07
    elig
    0.06
    Activations Density 0.481%

    No Known Activations