© 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. 17-LLAMASCOPE-RES-131K
    11. 85131
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to web protocols and URI formatting

    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
    py
    -0.09
     py
    -0.07
     Plastic
    -0.07
    ýš
    -0.06
    -page
    -0.06
    duk
    -0.06
    <=(
    -0.06
    etur
    -0.06
    IGHL
    -0.06
    pps
    -0.06
    POSITIVE LOGITS
     prefix
    0.13
    prefix
    0.10
    _prefix
    0.10
    Prefix
    0.10
    .prefix
    0.10
     prefixes
    0.09
    (prefix
    0.09
    -prefix
    0.09
     Prefix
    0.08
    refix
    0.08
    Activations Density 0.056%

    No Known Activations