© 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. 98429
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and institutions

    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
    egas
    -0.07
    ServiceProvider
    -0.07
    zug
    -0.07
    zá
    -0.07
     Morr
    -0.07
    ANO
    -0.07
    ipop
    -0.07
    taire
    -0.07
    hire
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
    åĸ
    0.06
    455
    0.06
    452
    0.06
    ool
    0.06
    oot
    0.06
    yl
    0.05
    isa
    0.05
    oola
    0.05
    ä»ĬæĹ¥
    0.05
    wu
    0.05
    Activations Density 0.149%

    No Known Activations