© 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 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. 29059
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and their association with nouns

    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
    Interop
    -0.08
    ADI
    -0.08
    eyh
    -0.07
    ugins
    -0.07
    adi
    -0.07
    luet
    -0.07
    UGH
    -0.07
     graf
    -0.07
    isposable
    -0.07
    WebRequest
    -0.07
    POSITIVE LOGITS
     ones
    0.08
    ing
    0.06
     Ones
    0.06
    ones
    0.06
     Bart
    0.06
     means
    0.06
     Koch
    0.06
     existence
    0.06
    æĸ
    0.06
     McCl
    0.06
    Activations Density 0.063%

    No Known Activations