© 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. 120258
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic research and historical documentation

    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
    aign
    -0.06
    endale
    -0.06
    usercontent
    -0.06
     داÙħ
    -0.06
    azen
    -0.06
    archives
    -0.06
     immobil
    -0.06
     traf
    -0.06
     pres
    -0.06
    .INSTANCE
    -0.06
    POSITIVE LOGITS
     treat
    0.09
    -volume
    0.08
     Treat
    0.08
     Volume
    0.08
     volume
    0.08
     Princip
    0.08
    STALL
    0.07
    adow
    0.07
     volumes
    0.07
    ož
    0.07
    Activations Density 0.077%

    No Known Activations