© 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. 15-LLAMASCOPE-RES-131K
    11. 90347
    Prev
    Next
    INDEX
    Explanations

    references to environmental and violent incidents

    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
    еÑĤелÑĮ
    -0.07
    ictim
    -0.07
    άνÏĦα
    -0.07
    ovatel
    -0.07
    _dc
    -0.06
    ело
    -0.06
    _AI
    -0.06
    ovice
    -0.06
    _callable
    -0.06
     tháºŃt
    -0.06
    POSITIVE LOGITS
     similarly
    0.12
     another
    0.09
     similar
    0.09
    Similarly
    0.08
    another
    0.08
     Similarly
    0.08
     Dit
    0.08
     likewise
    0.08
     ebenfalls
    0.07
    similar
    0.07
    Activations Density 0.006%

    No Known Activations