© 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. 28718
    Prev
    Next
    INDEX
    Explanations

    tokens and dates related to births and significant events

    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
    ards
    -0.08
    MimeType
    -0.07
    ilent
    -0.07
    ihat
    -0.07
    خر
    -0.07
    gewater
    -0.07
    culate
    -0.07
    _skb
    -0.06
    batis
    -0.06
    ipment
    -0.06
    POSITIVE LOGITS
    194
    0.06
    197
    0.06
     Tavern
    0.06
     rel
    0.06
    ango
    0.06
     raise
    0.06
    ANGO
    0.06
    Ïĥια
    0.06
    _script
    0.05
    RTL
    0.05
    Activations Density 0.004%

    No Known Activations