© 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. 87775
    Prev
    Next
    INDEX
    Explanations

    references to community influence in various contexts

    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
    /devices
    -0.07
     neutral
    -0.06
    jo
    -0.06
    _clock
    -0.06
    -neutral
    -0.06
    435
    -0.05
    åł
    -0.05
    رÙĪد
    -0.05
     PA
    -0.05
     Neutral
    -0.05
    POSITIVE LOGITS
     guides
    0.12
    guide
    0.11
     guide
    0.11
     Guides
    0.10
     Guide
    0.09
    Guide
    0.09
     GUIDE
    0.09
     influence
    0.08
     inspiration
    0.08
     guiding
    0.08
    Activations Density 0.125%

    No Known Activations