© 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. 93554
    Prev
    Next
    INDEX
    Explanations

    terms related to legislative measures and accountability in child and veteran protection laws

    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
    /MIT
    -0.07
    евеÑĢ
    -0.07
    uges
    -0.07
    _WM
    -0.07
    _FOREACH
    -0.07
    onta
    -0.07
    amax
    -0.07
    é³
    -0.07
    aint
    -0.07
    ::*
    -0.07
    POSITIVE LOGITS
     more
    0.07
     modern
    0.06
     Panda
    0.06
     commons
    0.06
     easier
    0.05
     tools
    0.05
     opt
    0.05
     existing
    0.05
     sue
    0.05
    /msg
    0.05
    Activations Density 0.041%

    No Known Activations