© 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. 17-LLAMASCOPE-RES-131K
    6. 125250
    Prev
    Next
    INDEX
    Explanations

    elements related to technical issue troubleshooting, specifically for kick starters

    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
     presence
    -0.07
    prox
    -0.06
    presence
    -0.06
    pus
    -0.06
     aproxim
    -0.06
     Presence
    -0.06
     vip
    -0.06
     Paz
    -0.06
    pecified
    -0.06
    Backend
    -0.06
    POSITIVE LOGITS
    ĵĺ
    0.07
    ysz
    0.07
    ystack
    0.07
     Edward
    0.06
    201
    0.06
    ubits
    0.06
    erne
    0.06
     Snowden
    0.06
    uner
    0.06
    à¥Įल
    0.06
    Activations Density 0.002%

    No Known Activations