© 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. 18435
    Prev
    Next
    INDEX
    Explanations

    inquiries about food preparation and cooking techniques

    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
    oj
    -0.06
    åĨ
    -0.06
    iad
    -0.06
    seys
    -0.06
     curs
    -0.06
     responsibilities
    -0.06
     Å¡to
    -0.05
     vej
    -0.05
    ald
    -0.05
     cul
    -0.05
    POSITIVE LOGITS
    inaire
    0.10
    ught
    0.07
    oggles
    0.07
    jvu
    0.07
    ');?>↵
    0.07
     ç±
    0.07
    ortho
    0.07
     Chambers
    0.07
    LEE
    0.07
    надлеж
    0.06
    Activations Density 0.041%

    No Known Activations