© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4182
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize convenience and making tasks simpler

    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
    ypi
    -0.09
    uraa
    -0.08
    ̣
    -0.08
    undles
    -0.07
    phis
    -0.07
    okoj
    -0.07
    æ®ĸ
    -0.07
    avl
    -0.07
     Dillon
    -0.07
    .partial
    -0.07
    POSITIVE LOGITS
    ullo
    0.06
    erre
    0.06
    istique
    0.06
    61
    0.06
     a
    0.06
     thereby
    0.06
    .component
    0.05
    514
    0.05
    erb
    0.05
    .getOwnProperty
    0.05
    Activations Density 0.010%

    No Known Activations