© 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. 15-LLAMASCOPE-RES-131K
    11. 86422
    Prev
    Next
    INDEX
    Explanations

    assignments or default values in programming context or code snippets

    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
    ervo
    -0.07
    ãĥ¬ãĥĵ
    -0.06
    á»ĭ
    -0.06
     zwar
    -0.06
    esco
    -0.06
    bucks
    -0.06
     å®
    -0.06
    ntax
    -0.06
    /******/
    -0.06
    лÑıв
    -0.06
    POSITIVE LOGITS
    orted
    0.06
    etto
    0.06
    =default
    0.06
    wood
    0.06
     Clark
    0.06
    gang
    0.06
    onto
    0.06
    élé
    0.06
    ameda
    0.06
    mer
    0.06
    Activations Density 0.006%

    No Known Activations