© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75843
    Prev
    Next
    INDEX
    Explanations

    concepts related to technology and autonomous systems

    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
    CRT
    -0.07
    uisine
    -0.07
    寿
    -0.07
    rug
    -0.06
    ancel
    -0.06
    incinn
    -0.06
    uset
    -0.06
    bounce
    -0.06
    ittel
    -0.06
    antha
    -0.06
    POSITIVE LOGITS
     vision
    0.10
     Vision
    0.09
     sensor
    0.08
    vision
    0.08
    Vision
    0.08
     Safety
    0.08
    _navigation
    0.07
    eyes
    0.07
     sensors
    0.07
     safety
    0.07
    Activations Density 0.007%

    No Known Activations