© 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. 26439
    Prev
    Next
    INDEX
    Explanations

    endpoints and assertions in code snippets

    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
    olland
    -0.06
    olly
    -0.06
     g
    -0.06
     Hol
    -0.06
    .IsNull
    -0.06
    lets
    -0.06
    ODB
    -0.05
     Wilkinson
    -0.05
     Moody
    -0.05
    ĽĦ
    -0.05
    POSITIVE LOGITS
    ãĤ·ãĥ¼
    0.08
    egis
    0.08
    Subsystem
    0.07
    vů
    0.07
    addtogroup
    0.07
    acons
    0.07
    hind
    0.07
    Anonymous
    0.07
    onym
    0.07
    obao
    0.07
    Activations Density 0.003%

    No Known Activations