© 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. 56003
    Prev
    Next
    INDEX
    Explanations

    instances of user engagement or comments in texts

    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
    ãĥĭãĥĥãĤ¯
    -0.06
    رÙģ
    -0.06
    yii
    -0.06
    .scalablytyped
    -0.06
    anc
    -0.06
    rompt
    -0.06
    à¹Ģหล
    -0.06
    LayoutManager
    -0.06
    itch
    -0.06
    ym
    -0.06
    POSITIVE LOGITS
    ompiler
    0.06
    stad
    0.06
    oksen
    0.06
    žel
    0.06
    аÑĢод
    0.06
     stdClass
    0.06
    leen
    0.06
    /Dk
    0.06
     Ying
    0.06
    #
    0.06
    Activations Density 0.002%

    No Known Activations