© 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. 103706
    Prev
    Next
    INDEX
    Explanations

    references to monitoring and oversight of health and behavioral standards

    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
    ulos
    -0.08
    ios
    -0.07
    ViewItem
    -0.06
    yi
    -0.06
     è¦
    -0.06
    holds
    -0.06
    omba
    -0.06
    hold
    -0.06
    IID
    -0.06
    clid
    -0.06
    POSITIVE LOGITS
     closely
    0.11
     progress
    0.10
    progress
    0.08
     trends
    0.07
    -progress
    0.07
     developments
    0.07
     Progress
    0.07
     affairs
    0.07
    lix
    0.07
     chặt
    0.07
    Activations Density 0.016%

    No Known Activations