© 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. 117844
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or significant quantities

    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
     cái
    -0.07
    غÙĦ
    -0.07
    ejs
    -0.07
     McCartney
    -0.07
    ibri
    -0.07
    ÑĤÑİ
    -0.06
    è³Ģ
    -0.06
    ril
    -0.06
    itat
    -0.06
    غاÙĦ
    -0.06
    POSITIVE LOGITS
     competitive
    0.10
     performance
    0.09
     sports
    0.09
     playing
    0.09
    competitive
    0.08
     training
    0.08
     skill
    0.08
     game
    0.08
    performance
    0.08
     Performance
    0.08
    Activations Density 0.002%

    No Known Activations