© 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. 58696
    Prev
    Next
    INDEX
    Explanations

    references to software systems and frameworks in a research 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
    oller
    -0.06
     ol
    -0.06
     Sche
    -0.06
     sort
    -0.06
     about
    -0.06
     Costa
    -0.06
     Staples
    -0.06
    jee
    -0.06
    ittel
    -0.05
     Shea
    -0.05
    POSITIVE LOGITS
     autogenerated
    0.07
    ogui
    0.07
    importe
    0.07
    ëĬ¥
    0.07
    izzo
    0.07
    alnız
    0.07
     automáticamente
    0.07
     frontend
    0.07
    -users
    0.06
    -user
    0.06
    Activations Density 0.007%

    No Known Activations