© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    references to notable people and cultural entities

    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
    hest
    -0.07
    insk
    -0.06
    á»Ļ
    -0.06
     entitled
    -0.06
     Orc
    -0.06
    Spoiler
    -0.06
    rome
    -0.06
    Japanese
    -0.06
     Edison
    -0.06
     Staples
    -0.06
    POSITIVE LOGITS
    phia
    0.08
    ÑĢаж
    0.07
     å°ij
    0.06
    ikki
    0.06
    icz
    0.06
    Ä±ÅŁÄ±
    0.06
     Buen
    0.06
     buna
    0.06
     поÑĩ
    0.06
     embassy
    0.06
    Activations Density 0.071%

    No Known Activations