© 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. 40164
    Prev
    Next
    INDEX
    Explanations

    references to specific geopolitical entities and 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
    _RPC
    -0.09
    CJK
    -0.09
    akis
    -0.08
    :params
    -0.08
     بازبÛĮÙĨÛĮ
    -0.08
    /null
    -0.08
    emand
    -0.08
     bÃłn
    -0.08
    icari
    -0.08
    opsis
    -0.08
    POSITIVE LOGITS
     reply
    0.12
     response
    0.11
     respond
    0.10
     replies
    0.09
    reply
    0.08
     replied
    0.08
     Reply
    0.08
     deny
    0.08
     responded
    0.07
     responds
    0.07
    Activations Density 0.054%

    No Known Activations