© 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. 62240
    Prev
    Next
    INDEX
    Explanations

    scientific data and experimental results

    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
     Manning
    -0.06
    ¸
    -0.06
     Pratt
    -0.06
     sal
    -0.06
     traction
    -0.06
    apr
    -0.06
     PROGMEM
    -0.06
     Class
    -0.05
     mechan
    -0.05
     secret
    -0.05
    POSITIVE LOGITS
     Cary
    0.08
    ampil
    0.08
     cry
    0.07
    utas
    0.07
    Bru
    0.07
    ringe
    0.07
    ëĭ´
    0.07
    recated
    0.07
    cry
    0.07
     chamber
    0.07
    Activations Density 0.035%

    No Known Activations