© 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. 15-LLAMASCOPE-RES-131K
    11. 90614
    Prev
    Next
    INDEX
    Explanations

    numerical data regarding population and resources

    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
    loff
    -0.07
    zano
    -0.07
    riad
    -0.07
    variants
    -0.07
    istani
    -0.07
    slideUp
    -0.07
    _inches
    -0.07
    imeters
    -0.07
    zure
    -0.07
    vided
    -0.07
    POSITIVE LOGITS
     concrete
    0.07
    385
    0.07
     thousands
    0.07
     millions
    0.06
    ÙĪÙĨت
    0.06
     hundreds
    0.06
     out
    0.06
    erin
    0.05
    лини
    0.05
    detach
    0.05
    Activations Density 0.024%

    No Known Activations