© 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. 39115
    Prev
    Next
    INDEX
    Explanations

    significant references or mentions in the text, especially around individuals and government activities

    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
    ë²Į
    -0.07
    .elapsed
    -0.06
     Petit
    -0.06
     favourites
    -0.06
    اÙħبر
    -0.06
    %A
    -0.06
    abay
    -0.06
    issen
    -0.06
    AREST
    -0.06
     Crab
    -0.06
    POSITIVE LOGITS
     till
    0.07
     era
    0.06
     rehab
    0.06
    oref
    0.06
    oso
    0.06
     soccer
    0.06
     vis
    0.06
     Brit
    0.06
     reflex
    0.06
    ulsion
    0.06
    Activations Density 0.000%

    No Known Activations