© 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. 17816
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

    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
    ÑĢин
    -0.08
    ovit
    -0.07
    agon
    -0.06
    inger
    -0.06
    cess
    -0.06
     Stable
    -0.06
    coma
    -0.06
     McG
    -0.06
    stable
    -0.06
    pson
    -0.06
    POSITIVE LOGITS
    ause
    0.07
     regards
    0.07
     ilk
    0.07
     Blowjob
    0.06
    ovy
    0.06
    isposable
    0.06
    otland
    0.06
     ê°ĻìĿ´
    0.06
     everybody
    0.06
    AAD
    0.06
    Activations Density 0.016%

    No Known Activations