© 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. 104481
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations involving addition and multiplication

    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
    riz
    -0.07
    eah
    -0.07
    alance
    -0.07
    isor
    -0.06
    apia
    -0.06
    ãĥ¼ãĥª
    -0.06
    ustum
    -0.06
    çĦ¶
    -0.06
    ajo
    -0.06
    umu
    -0.06
    POSITIVE LOGITS
    /-
    0.08
    ++++
    0.07
    togroup
    0.06
    -ons
    0.06
    sts
    0.06
    itionally
    0.06
    itivity
    0.06
    /or
    0.06
    bers
    0.06
     Homes
    0.06
    Activations Density 0.114%

    No Known Activations