© 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. 15880
    Prev
    Next
    INDEX
    Explanations

    terms associated with transportation and architecture

    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
    ITY
    -0.07
    ën
    -0.07
    plier
    -0.07
    ourke
    -0.06
    istically
    -0.06
    inness
    -0.06
    iddet
    -0.06
    fra
    -0.06
    ierz
    -0.06
    ffective
    -0.06
    POSITIVE LOGITS
    ations
    0.14
    ively
    0.13
    ive
    0.12
    ors
    0.12
    ino
    0.12
    ative
    0.11
    ation
    0.11
    um
    0.11
    ible
    0.11
    eur
    0.10
    Activations Density 0.058%

    No Known Activations