© 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. 93516
    Prev
    Next
    INDEX
    Explanations

    references to historical conflicts and their complexities

    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
    aret
    -0.06
    Alarm
    -0.06
    yar
    -0.06
    acker
    -0.06
     average
    -0.06
    alarm
    -0.06
     alarm
    -0.06
     recent
    -0.06
    CLK
    -0.06
    íıī
    -0.06
    POSITIVE LOGITS
     flooding
    0.07
     winning
    0.07
     floods
    0.07
    urtle
    0.07
     starving
    0.07
    through
    0.06
     Winning
    0.06
     starvation
    0.06
    _WIN
    0.06
     humble
    0.06
    Activations Density 0.041%

    No Known Activations