© 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 EvalsExportsinterp-engineNEWAPI 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. 58412
    Prev
    Next
    INDEX
    Explanations

    numerical data related to dates

    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
    çĻº
    -0.07
    underscore
    -0.07
    ¶Į
    -0.07
    @update
    -0.07
    anou
    -0.07
     Lah
    -0.07
    464
    -0.07
    reste
    -0.07
    earer
    -0.07
    åħIJ
    -0.07
    POSITIVE LOGITS
    vik
    0.06
    å±ĭ
    0.06
    ise
    0.06
    inne
    0.06
     oro
    0.06
    /src
    0.05
    angan
    0.05
    aram
    0.05
    ød
    0.05
    ame
    0.05
    Activations Density 0.000%

    No Known Activations