© 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. 9-LLAMASCOPE-RES-131K
    11. 97577
    Prev
    Next
    INDEX
    Explanations

    important numerical statistics related to health and safety

    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
    ãģ¹ãģ¦
    -0.06
    ution
    -0.06
    .slim
    -0.06
    /reference
    -0.06
    556
    -0.06
    antwort
    -0.06
    resi
    -0.06
    dera
    -0.06
    ived
    -0.06
    ING
    -0.06
    POSITIVE LOGITS
    tl
    0.08
    essler
    0.08
    SError
    0.07
     GetLastError
    0.07
    .exc
    0.06
    unden
    0.06
     Incontri
    0.06
     Renders
    0.06
    wiÄħ
    0.06
    oreach
    0.06
    Activations Density 0.034%

    No Known Activations