© 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. 40792
    Prev
    Next
    INDEX
    Explanations

    phrases related to production and environmental impact

    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
    è¡
    -0.07
    gard
    -0.07
     Opport
    -0.07
     Opr
    -0.06
    olicit
    -0.06
    gaard
    -0.06
     Charge
    -0.06
    EXIT
    -0.06
    bsite
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
     circulation
    0.10
     society
    0.08
     circulating
    0.07
     pool
    0.07
     public
    0.07
    _Release
    0.07
    Helmet
    0.07
     market
    0.07
     supply
    0.07
    åħ
    0.06
    Activations Density 0.103%

    No Known Activations