© 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. 30310
    Prev
    Next
    INDEX
    Explanations

    instructions related to flooring installation and costs

    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
    ,
    -0.07
    anga
    -0.06
     e
    -0.06
    umann
    -0.06
    Âł
    -0.06
     mart
    -0.05
     leaf
    -0.05
     nat
    -0.05
     (
    -0.05
     soup
    -0.05
    POSITIVE LOGITS
    éĿ¢ç©į
    0.16
    éĿ¢ç§¯
    0.15
     area
    0.15
     Area
    0.14
    Area
    0.14
    area
    0.14
     AREA
    0.14
    AREA
    0.13
    -area
    0.13
    coverage
    0.13
    Activations Density 0.113%

    No Known Activations