© 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. 94011
    Prev
    Next
    INDEX
    Explanations

    expressions indicating duality or contrasts in experiences

    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
    598
    -0.08
    crast
    -0.08
    á»ħ
    -0.08
    ection
    -0.07
    Portfolio
    -0.07
    596
    -0.07
    ucci
    -0.06
    çĺ
    -0.06
    jo
    -0.06
    999
    -0.06
    POSITIVE LOGITS
     extremes
    0.07
     macro
    0.07
     worlds
    0.07
    macro
    0.07
     linear
    0.06
     conventional
    0.06
     recap
    0.06
     fast
    0.06
     tradition
    0.06
     traditional
    0.06
    Activations Density 0.018%

    No Known Activations