© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements and their attributes

    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
    iros
    -0.08
    aepernick
    -0.07
    vyk
    -0.07
    peare
    -0.07
    оÑĩ
    -0.07
     Ulus
    -0.07
    endencies
    -0.07
    pac
    -0.07
    packed
    -0.07
    Compound
    -0.06
    POSITIVE LOGITS
     mobil
    0.07
     temporarily
    0.06
     Ray
    0.06
     outside
    0.06
     Mobil
    0.06
     temporary
    0.06
    astreet
    0.06
     tempor
    0.06
     Tam
    0.06
     Marty
    0.06
    Activations Density 0.012%

    No Known Activations