© 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. 90617
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to specific categories

    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
    -
    -0.06
    ↵
    -0.06
     .
    -0.06
     Brick
    -0.06
    ,
    -0.05
    oused
    -0.05
    ouses
    -0.05
    cmc
    -0.05
     (
    -0.05
    heel
    -0.05
    POSITIVE LOGITS
    DataExchange
    0.08
    ,LOCATION
    0.07
    سطس
    0.07
    kul
    0.07
    ecies
    0.07
     nues
    0.07
    MemoryWarning
    0.07
    StringEncoding
    0.07
    usercontent
    0.07
    ekl
    0.07
    Activations Density 0.004%

    No Known Activations