© 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. 83736
    Prev
    Next
    INDEX
    Explanations

    instances of the term "defeated" and other related victory-related terms in competitive 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
    ãĥĨãĥ«
    -0.09
    anki
    -0.08
    otine
    -0.07
    маз
    -0.07
    /platform
    -0.07
    rowable
    -0.07
    oux
    -0.07
    οÏĤ
    -0.07
     dÄ±ÅŁÄ±nda
    -0.07
    tent
    -0.07
    POSITIVE LOGITS
     fellow
    0.08
     hap
    0.06
    ments
    0.06
     doubles
    0.06
     visiting
    0.06
    hap
    0.06
     us
    0.06
    ively
    0.06
     in
    0.06
     him
    0.06
    Activations Density 0.022%

    No Known Activations