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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15075
    Prev
    Next
    INDEX
    Explanations

    instances of political discourse and societal concerns

    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
    Anywhere
    -0.08
    inand
    -0.07
    alÄ±ÅŁ
    -0.07
    Ỽi
    -0.07
    CriticalSection
    -0.07
    leme
    -0.07
    processable
    -0.07
    LARI
    -0.07
    ίνει
    -0.07
    .nan
    -0.07
    POSITIVE LOGITS
     if
    0.08
     another
    0.08
     maybe
    0.07
     bottom
    0.07
     finally
    0.06
     Bottom
    0.06
     America
    0.06
     If
    0.06
    Bottom
    0.06
    myp
    0.06
    Activations Density 0.020%

    No Known Activations