© 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. 16530
    Prev
    Next
    INDEX
    Explanations

    specific models and features of Microsoft Surface devices

    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
    à¹Ĩ
    -0.06
     (*((
    -0.06
    atur
    -0.06
     ga
    -0.06
    .scalablytyped
    -0.06
    cone
    -0.06
     McMaster
    -0.06
    ко
    -0.06
    LOSE
    -0.06
    ERSION
    -0.05
    POSITIVE LOGITS
     series
    0.08
     serie
    0.08
    ãĤ·ãĥªãĥ¼ãĤº
    0.08
    .touch
    0.07
    -series
    0.07
     оÑģÑĮ
    0.07
    /apt
    0.07
    ç³»åĪĹ
    0.07
    ®
    0.06
    monds
    0.06
    Activations Density 0.015%

    No Known Activations