© 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. 89670
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements, particularly in a code-like structure

    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
    rible
    -0.07
    imits
    -0.07
    dzi
    -0.07
    riz
    -0.06
    \-
    -0.06
    rens
    -0.06
     DevComponents
    -0.06
    luv
    -0.06
    inkle
    -0.06
    illet
    -0.06
    POSITIVE LOGITS
    ual
    0.06
    gate
    0.06
    اÙħÛĮ
    0.06
     Lif
    0.06
     Pep
    0.06
    PART
    0.05
    .proc
    0.05
    ultipart
    0.05
    pathname
    0.05
     Perkins
    0.05
    Activations Density 0.000%

    No Known Activations