© 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. 31072
    Prev
    Next
    INDEX
    Explanations

    specific brands or titles related to games or gaming publications

    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
    ibbon
    -0.06
    adol
    -0.06
    еж
    -0.06
    RefCount
    -0.05
     couples
    -0.05
    odu
    -0.05
    cob
    -0.05
    aoke
    -0.05
    esan
    -0.05
     Wikip
    -0.05
    POSITIVE LOGITS
     Records
    0.09
     Productions
    0.09
     Yayın
    0.08
     Kültür
    0.08
     Press
    0.08
    #ad
    0.07
    pagesize
    0.07
     ucwords
    0.07
    .LayoutParams
    0.07
     Latina
    0.07
    Activations Density 0.097%

    No Known Activations