© 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. 28975
    Prev
    Next
    INDEX
    Explanations

    terms related to underlying issues and root causes in social or medical contexts

    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
    /assert
    -0.07
    eyen
    -0.06
    kud
    -0.06
    onium
    -0.06
    PostExecute
    -0.06
    omik
    -0.06
    uj
    -0.06
    zon
    -0.06
     persön
    -0.06
    seud
    -0.05
    POSITIVE LOGITS
     underlying
    0.17
     Causes
    0.09
     causes
    0.09
     caus
    0.09
     source
    0.08
     sources
    0.08
    æºIJ
    0.08
     cause
    0.07
    sources
    0.07
     Address
    0.07
    Activations Density 0.024%

    No Known Activations