© 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. 84045
    Prev
    Next
    INDEX
    Explanations

    concepts related to sustainability and accountability in organizations

    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
     Nash
    -0.06
    bay
    -0.06
    stile
    -0.06
    FTA
    -0.06
     Lyon
    -0.06
    ecc
    -0.06
     port
    -0.05
    Advertisement
    -0.05
    bjerg
    -0.05
     ports
    -0.05
    POSITIVE LOGITS
    auth
    0.10
     auth
    0.09
     authenticity
    0.09
    Auth
    0.09
     Authentic
    0.09
     Auth
    0.08
     authentic
    0.08
    Campaign
    0.07
    .native
    0.07
    Ãło
    0.07
    Activations Density 0.001%

    No Known Activations