© 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. 17-LLAMASCOPE-RES-131K
    11. 16895
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and numerical data

    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
    [s
    -0.06
    ages
    -0.06
    ipt
    -0.06
    iegel
    -0.06
    iral
    -0.06
    acific
    -0.06
     cord
    -0.05
    owell
    -0.05
    eyer
    -0.05
     alone
    -0.05
    POSITIVE LOGITS
    گاÙĨÛĮ
    0.09
    ednou
    0.09
     Bilg
    0.08
    _OBJC
    0.07
    aÄį
    0.07
    swer
    0.07
    reno
    0.07
    ekil
    0.07
    erece
    0.07
    ymm
    0.07
    Activations Density 0.116%

    No Known Activations