© 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. 87564
    Prev
    Next
    INDEX
    Explanations

    articles and descriptive phrases that signify qualities or characteristics of nouns

    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
     dit
    -0.07
     rates
    -0.06
    acha
    -0.06
     dara
    -0.06
    ema
    -0.06
     sealing
    -0.06
     pregnant
    -0.05
     ÐľÐ¸Ðº
    -0.05
     coc
    -0.05
     Rig
    -0.05
    POSITIVE LOGITS
    ECTOR
    0.08
    ¼åIJĪ
    0.08
    uteur
    0.07
    uthor
    0.07
    atural
    0.07
    ôme
    0.07
    лага
    0.07
    leta
    0.07
    鼨
    0.07
    tring
    0.07
    Activations Density 0.039%

    No Known Activations