© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83883
    Prev
    Next
    INDEX
    Explanations

    biochemical terms and processes related to viral research

    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
    /exec
    -0.06
    uir
    -0.06
    otton
    -0.06
    ré
    -0.06
    usu
    -0.06
    apis
    -0.06
    359
    -0.06
    _supp
    -0.06
     Immutable
    -0.06
    изнеÑģ
    -0.06
    POSITIVE LOGITS
    -labelled
    0.09
    -tag
    0.08
     tracer
    0.08
    Äįer
    0.07
    laden
    0.06
     label
    0.06
    -l
    0.06
    ÙĬÙĨÙĩ
    0.06
    robe
    0.06
    auer
    0.06
    Activations Density 0.026%

    No Known Activations