© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56752
    Prev
    Next
    INDEX
    Explanations

    phrases indicating governmental or organizational plans and reforms

    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
    aren
    -0.07
    andal
    -0.07
     whilst
    -0.06
    etal
    -0.06
     kred
    -0.06
    hound
    -0.06
    :description
    -0.06
     Äijại
    -0.06
     cru
    -0.06
     themselves
    -0.06
    POSITIVE LOGITS
     effort
    0.09
     efforts
    0.09
     broader
    0.09
     larger
    0.08
     Sür
    0.07
    ongo
    0.07
     attempts
    0.07
     an
    0.07
     ongoing
    0.07
    ipple
    0.07
    Activations Density 0.009%

    No Known Activations