© 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. 17-LLAMASCOPE-RES-131K
    11. 93193
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts related to function accessibility and variable management

    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
    oload
    -0.09
    ousse
    -0.07
    itchen
    -0.07
    ::__
    -0.07
    ingen
    -0.07
    gle
    -0.07
    onet
    -0.07
    peria
    -0.07
    ä¼ı
    -0.07
    Mess
    -0.07
    POSITIVE LOGITS
    reference
    0.07
     reference
    0.07
     Ownership
    0.07
     ownership
    0.07
     imm
    0.07
    mere
    0.07
     Reference
    0.07
    -reference
    0.07
     references
    0.07
    Ownership
    0.07
    Activations Density 0.005%

    No Known Activations