© 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. 89748
    Prev
    Next
    INDEX
    Explanations

    terms related to themes and WordPress theme options

    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
    .scalablytyped
    -0.07
    onal
    -0.06
    ional
    -0.06
     flight
    -0.06
    lon
    -0.06
    -purpose
    -0.06
    wy
    -0.05
    ona
    -0.05
    ents
    -0.05
     reg
    -0.05
    POSITIVE LOGITS
    нина
    0.09
    UnderTest
    0.08
    вод
    0.08
    нин
    0.07
    ventus
    0.07
    arus
    0.07
    inde
    0.07
    ijken
    0.07
     Fundamental
    0.07
    FUN
    0.07
    Activations Density 0.007%

    No Known Activations