© 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. 79949
    Prev
    Next
    INDEX
    Explanations

    references to prices and events related to travel or accommodations

    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
    .za
    -0.08
    Emoji
    -0.08
    atron
    -0.08
    Fullscreen
    -0.08
    overe
    -0.08
    οκ
    -0.08
    .GPIO
    -0.08
    .gf
    -0.07
    дÑĢом
    -0.07
    loat
    -0.07
    POSITIVE LOGITS
    200
    0.07
     Marketplace
    0.06
     or
    0.06
    aque
    0.06
     pedig
    0.05
     free
    0.05
    å·±
    0.05
     Axis
    0.05
     <!
    0.05
    ↵
    0.05
    Activations Density 0.000%

    No Known Activations