© 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. 9-LLAMASCOPE-RES-131K
    11. 96285
    Prev
    Next
    INDEX
    Explanations

    references to flooring conditions and quality

    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
    overe
    -0.07
    undy
    -0.07
    füh
    -0.07
    hoa
    -0.07
    oard
    -0.07
    erialized
    -0.07
    isay
    -0.07
    CustomAttributes
    -0.07
    erokee
    -0.07
    POSITIVE LOGITS
     Gravity
    0.07
    SB
    0.06
     lev
    0.06
     grave
    0.06
     gravity
    0.06
     SB
    0.05
     aging
    0.05
     grav
    0.05
     straw
    0.05
    nis
    0.05
    Activations Density 0.006%

    No Known Activations