© 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. 130252
    Prev
    Next
    INDEX
    Explanations

    terminology related to nuclear reactions and isotopes in scientific contexts

    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
     dil
    -0.06
     living
    -0.06
     environmental
    -0.06
    -like
    -0.06
     yes
    -0.05
     intriguing
    -0.05
     ask
    -0.05
     right
    -0.05
     fascinating
    -0.05
    agram
    -0.05
    POSITIVE LOGITS
     onDataChange
    0.09
    culate
    0.08
    Summon
    0.08
    puted
    0.07
    ówn
    0.07
    TOTYPE
    0.07
    Tables
    0.07
    opolitan
    0.07
    .NORMAL
    0.07
    Ùİج
    0.07
    Activations Density 0.028%

    No Known Activations