© 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. 14629
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with scientific institutions and their research outputs

    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
    opard
    -0.07
    ogan
    -0.07
    landa
    -0.07
    جد
    -0.06
     Whe
    -0.06
    جÙĦ
    -0.06
    wyn
    -0.06
    obus
    -0.06
    opak
    -0.06
     underground
    -0.06
    POSITIVE LOGITS
    embro
    0.07
    /gui
    0.06
    keyword
    0.06
    /MIT
    0.06
     Thorn
    0.06
    -prev
    0.06
    ians
    0.06
     Brock
    0.06
    èĦij
    0.06
    ÏĢον
    0.06
    Activations Density 0.000%

    No Known Activations