© 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. 30709
    Prev
    Next
    INDEX
    Explanations

    the frequent use of the word "the" and variations of "your" and "our."

    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
    ayo
    -0.07
    oft
    -0.07
    med
    -0.06
    wright
    -0.06
    CF
    -0.06
    İ
    -0.06
    waters
    -0.06
    neau
    -0.06
    ruba
    -0.06
    Ĺı
    -0.06
    POSITIVE LOGITS
    pNet
    0.08
     ucwords
    0.07
    ÑıÑĩ
    0.07
    isser
    0.07
    oley
    0.07
    аÑĢÑĩ
    0.07
    (TM
    0.06
    аки
    0.06
    etas
    0.06
    iв
    0.06
    Activations Density 0.005%

    No Known Activations