© 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 EvalsExportsAPI 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. 58645
    Prev
    Next
    INDEX
    Explanations

    references to thoroughness and care in processes or evaluations

    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
    ë²Į
    -0.08
    ç±į
    -0.08
    à¹Ĩ
    -0.08
    ropol
    -0.07
    idine
    -0.07
     Lawson
    -0.07
    nie
    -0.07
    ANNEL
    -0.07
    uchen
    -0.07
    nga
    -0.07
    POSITIVE LOGITS
    ainted
    0.07
    ìĤ¬íķŃ
    0.06
     afore
    0.06
    .SDK
    0.06
    igne
    0.06
     prob
    0.06
     conducted
    0.06
    ountains
    0.06
    outs
    0.06
    ForObject
    0.06
    Activations Density 0.001%

    No Known Activations