© 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. 119800
    Prev
    Next
    INDEX
    Explanations

    the phrase "Find" followed by details on searches or inquiries

    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
    andum
    -0.06
    iese
    -0.06
     Blank
    -0.06
    utes
    -0.06
    angel
    -0.06
     Kits
    -0.06
     Benjamin
    -0.06
     versa
    -0.05
     outdoors
    -0.05
    laden
    -0.05
    POSITIVE LOGITS
    owler
    0.07
    çĵ
    0.07
    astle
    0.07
    ëͰ
    0.07
    CHIP
    0.07
    ìŀ¡
    0.07
    oggles
    0.06
    /stats
    0.06
    949
    0.06
    emi
    0.06
    Activations Density 0.002%

    No Known Activations