© 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. 39084
    Prev
    Next
    INDEX
    Explanations

    phrases related to simplification processes

    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
    ảo
    -0.07
    Ģ
    -0.06
    dic
    -0.06
    ãģ£ãģ¡
    -0.06
    tü
    -0.06
    سÙĪÙĨ
    -0.06
    bir
    -0.06
     selber
    -0.06
     bouts
    -0.06
    012
    -0.06
    POSITIVE LOGITS
     transitions
    0.07
     transition
    0.07
     task
    0.07
     process
    0.07
     lives
    0.07
     Ñģобой
    0.07
     tasks
    0.06
     procedure
    0.06
     quot
    0.06
    transition
    0.06
    Activations Density 0.018%

    No Known Activations