© 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. 235
    Prev
    Next
    INDEX
    Explanations

    discussions and analyses involving comparisons and consistency in measurements or arguments

    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
    zeichnet
    -0.07
    èn
    -0.06
    rong
    -0.06
    cek
    -0.06
    zeich
    -0.06
    erne
    -0.06
     dub
    -0.06
     ben
    -0.05
     pass
    -0.05
     derivatives
    -0.05
    POSITIVE LOGITS
     apples
    0.10
     comparisons
    0.09
     comparison
    0.09
    comparison
    0.09
     Comparison
    0.09
     compar
    0.09
     comparable
    0.08
     comparing
    0.08
     comparator
    0.08
    errupted
    0.08
    Activations Density 0.027%

    No Known Activations