© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1472
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to software or programming processes

    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
    ,...↵↵
    -0.07
    sı
    -0.07
    qli
    -0.07
    toi
    -0.07
    ä¸ļ
    -0.07
    wins
    -0.07
    ãģ¾ãģļ
    -0.07
    luet
    -0.07
    _Session
    -0.06
    جÙĬ
    -0.06
    POSITIVE LOGITS
     hopefully
    0.08
    asty
    0.07
     indeed
    0.07
     wherever
    0.06
     
    0.06
     as
    0.06
     accordingly
    0.06
     now
    0.06
    gado
    0.06
    apes
    0.06
    Activations Density 0.011%

    No Known Activations