© 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. 127139
    Prev
    Next
    INDEX
    Explanations

    words related to the chemical properties or classifications of substances

    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
    ler
    -0.09
    ylvania
    -0.08
    eler
    -0.08
    lemen
    -0.08
    ality
    -0.08
    le
    -0.07
    lip
    -0.07
    laus
    -0.07
    lessly
    -0.07
    low
    -0.07
    POSITIVE LOGITS
    ameda
    0.10
    igned
    0.09
    onso
    0.08
    phabet
    0.08
    entine
    0.08
    ıcı
    0.07
    igi
    0.07
    gebra
    0.07
    ughter
    0.07
    ifornia
    0.07
    Activations Density 0.030%

    No Known Activations