© 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. 2200
    Prev
    Next
    INDEX
    Explanations

    ingredients and food-related terms

    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
    amac
    -0.08
    æ§
    -0.07
    (æ°´
    -0.07
    apiro
    -0.07
    elerik
    -0.07
    utc
    -0.07
    isu
    -0.07
    à¥ģà¤ļ
    -0.07
     aggress
    -0.07
    ÄĤ
    -0.07
    POSITIVE LOGITS
     yours
    0.10
     ours
    0.09
    mine
    0.09
     theirs
    0.08
     mine
    0.07
     Mine
    0.07
     hers
    0.06
     Yours
    0.06
    Mine
    0.06
     recreational
    0.06
    Activations Density 0.100%

    No Known Activations