© 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. 94884
    Prev
    Next
    INDEX
    Explanations

    keywords associated with adjustable height desks and their features

    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
    door
    -0.07
     tie
    -0.06
    éĻ¢
    -0.06
    uiten
    -0.06
    tie
    -0.06
     att
    -0.06
     tied
    -0.06
     Outside
    -0.06
    gate
    -0.06
    fillna
    -0.06
    POSITIVE LOGITS
    åĬŀåħ¬
    0.12
    office
    0.12
     office
    0.12
     desk
    0.11
     Desk
    0.10
     Office
    0.10
    Office
    0.10
    desk
    0.10
    Desk
    0.10
    -office
    0.10
    Activations Density 0.010%

    No Known Activations