Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56063
    Prev
    Next
    INDEX
    Explanations

    instances of error handling or exceptions in code

    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
    ensch
    -0.09
    ADED
    -0.07
    enz
    -0.07
    -fontawesome
    -0.06
    dej
    -0.06
    ãĤ¥
    -0.06
    eneg
    -0.06
    ekil
    -0.06
    åıĤ
    -0.06
     sông
    -0.06
    POSITIVE LOGITS
    getMessage
    0.07
     Message
    0.07
    .message
    0.06
     message
    0.06
    AndGet
    0.06
    .getMessage
    0.06
     messages
    0.06
     Messages
    0.06
    StackTrace
    0.06
     Trustees
    0.06
    Activations Density 0.006%

    No Known Activations