© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61272
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other connective phrases that indicate relationships or associations in the text

    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
    .scalablytyped
    -0.09
    activex
    -0.08
    ë³
    -0.08
    ìľ¼ëĭĪ
    -0.08
    HeaderCode
    -0.07
    BackingField
    -0.07
     destinationViewController
    -0.07
    leyin
    -0.07
     Wikispecies
    -0.07
    ResourceManager
    -0.07
    POSITIVE LOGITS
    /or
    0.12
     other
    0.07
    acles
    0.07
    other
    0.07
    ame
    0.06
     Con
    0.06
    ait
    0.06
     th
    0.06
     /
    0.06
    oi
    0.06
    Activations Density 0.068%

    No Known Activations