© 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. 4474
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and support initiatives

    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
     rooms
    -0.07
     IOC
    -0.07
    /Dk
    -0.07
    å¶
    -0.07
    CEPTION
    -0.07
     hallway
    -0.07
     skiing
    -0.06
    важ
    -0.06
    é±¼
    -0.06
     Olympic
    -0.06
    POSITIVE LOGITS
    éŁ³æ¥½
    0.07
    ucci
    0.07
     park
    0.07
    tent
    0.07
    ifar
    0.07
     ìŀĶ
    0.07
     tents
    0.07
     music
    0.07
    platz
    0.07
     tent
    0.06
    Activations Density 0.018%

    No Known Activations