© 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. 61508
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols

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

    Punctuation marks (period or question mark) followed by closing brackets that mark the end of mathematical statements or questions in academic/educational content.

    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
     Bust
    -0.08
    hou
    -0.06
    ãĥĥãĥĪ
    -0.06
     bust
    -0.06
    DIC
    -0.06
     Works
    -0.06
    rael
    -0.06
    Works
    -0.06
    tit
    -0.06
    lesia
    -0.06
    POSITIVE LOGITS
    Ñģклад
    0.09
    ATOR
    0.07
    iceps
    0.07
    ocaust
    0.07
    å·±
    0.07
    inka
    0.07
    rix
    0.07
    roman
    0.07
    ivec
    0.07
    inke
    0.06
    Activations Density 0.035%

    No Known Activations