© 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. 15132
    Prev
    Next
    INDEX
    Explanations

    references to activities and lifestyle descriptions

    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
    .scalablytyped
    -0.07
     forg
    -0.07
    «ĺ
    -0.07
    assen
    -0.07
     Puzzle
    -0.07
    ettle
    -0.06
    buie
    -0.06
    ÑĦÑĤ
    -0.06
    elig
    -0.06
     pac
    -0.06
    POSITIVE LOGITS
    aires
    0.06
    CHO
    0.06
     Tep
    0.06
     cum
    0.06
    ÄĽÅ¾
    0.06
     finest
    0.05
     cord
    0.05
     Cummings
    0.05
    तर
    0.05
    ÑĶм
    0.05
    Activations Density 0.022%

    No Known Activations