© 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. 28514
    Prev
    Next
    INDEX
    Explanations

    references to social classes and their dynamics

    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
    qui
    -0.07
    mailer
    -0.07
     journalistic
    -0.06
    å¹³æĪIJ
    -0.06
     fullest
    -0.06
     superclass
    -0.06
    meer
    -0.06
    acker
    -0.06
    intl
    -0.06
    à¹Ħà¸ĭ
    -0.06
    POSITIVE LOGITS
     dunk
    0.06
     physic
    0.06
     tavern
    0.06
     mime
    0.06
    814
    0.06
    asmus
    0.06
    ROID
    0.06
    /commons
    0.06
    -pills
    0.06
    ongsTo
    0.06
    Activations Density 0.016%

    No Known Activations