© 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. 94678
    Prev
    Next
    INDEX
    Explanations

    web-related terms and elements

    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
    ocommerce
    -0.06
    502
    -0.06
    rades
    -0.06
    ÄĽ
    -0.05
    784
    -0.05
     lifetime
    -0.05
     propos
    -0.05
     beaut
    -0.05
     Lifetime
    -0.05
    740
    -0.05
    POSITIVE LOGITS
    .nih
    0.08
    uder
    0.08
     teb
    0.08
    egov
    0.08
     iht
    0.08
    #__
    0.08
    IDD
    0.07
    onda
    0.07
    oki
    0.07
    .xx
    0.07
    Activations Density 0.001%

    No Known Activations