© 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. 74680
    Prev
    Next
    INDEX
    Explanations

    references to social issues regarding education and inequality

    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
    HeaderCode
    -0.07
    UsageId
    -0.07
     VÅ¡ech
    -0.07
    hlen
    -0.07
    SupportedContent
    -0.07
    vanished
    -0.07
    (æ°´
    -0.07
    halt
    -0.07
    YTE
    -0.07
    rezent
    -0.06
    POSITIVE LOGITS
     nobody
    0.08
     rejects
    0.07
     desperation
    0.07
     bottom
    0.07
     desperate
    0.06
     cheaper
    0.06
     Bottom
    0.06
     unwanted
    0.06
     low
    0.06
    oran
    0.06
    Activations Density 0.033%

    No Known Activations