© 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. 103553
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or numerical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References to digits, decimal places, or numeric representations in code or mathematical contexts, often appearing in parameters that specify precision, formatting, or numeric parsing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    erg
    -0.07
     Scha
    -0.06
    .FLAG
    -0.06
    :\/\/
    -0.06
     Quint
    -0.06
    ozem
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    ož
    -0.06
     schön
    -0.06
    edb
    -0.06
    POSITIVE LOGITS
     å¤ı
    0.07
     Taste
    0.07
     taste
    0.06
    iao
    0.06
    .precision
    0.06
     cheap
    0.06
    .ie
    0.06
    iams
    0.06
    precision
    0.06
    prec
    0.06
    Activations Density 0.009%

    No Known Activations