© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78268
    Prev
    Next
    INDEX
    Explanations

    words related to services and business operations

    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
    igers
    -0.08
    eyh
    -0.07
    ulumi
    -0.07
    Ỽt
    -0.07
     åıĮ线
    -0.07
    egot
    -0.07
     norge
    -0.07
    çµ
    -0.07
    pell
    -0.07
    ngen
    -0.07
    POSITIVE LOGITS
     tree
    0.10
    /tree
    0.09
     arb
    0.09
     Tree
    0.08
    (tree
    0.08
     trunk
    0.07
    .Tree
    0.07
     TREE
    0.07
     trees
    0.07
     branches
    0.07
    Activations Density 0.001%

    No Known Activations