© 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. 82850
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics and measurements related to performance or production

    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
    каÑģ
    -0.07
    zell
    -0.07
    vyk
    -0.07
    owell
    -0.07
    ä¹ħ
    -0.07
    kest
    -0.07
    isku
    -0.07
    пÑĢ
    -0.07
    icorn
    -0.06
    egal
    -0.06
    POSITIVE LOGITS
     compared
    0.09
     than
    0.07
    auen
    0.07
     per
    0.06
    ann
    0.06
     Convention
    0.06
    en
    0.06
     doubles
    0.06
    å°ĭ
    0.06
     fragment
    0.06
    Activations Density 0.027%

    No Known Activations