© 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. 15-LLAMASCOPE-RES-131K
    11. 766
    Prev
    Next
    INDEX
    Explanations

    references to major plot twists and character developments in storytelling

    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
    SGlobal
    -0.07
     мел
    -0.07
     antlr
    -0.07
    jeme
    -0.07
    elsif
    -0.07
    nech
    -0.07
    uw
    -0.07
    _vue
    -0.07
    _mA
    -0.07
    xea
    -0.06
    POSITIVE LOGITS
     story
    0.06
    angan
    0.06
     macro
    0.06
    kowski
    0.06
     set
    0.06
     conservatism
    0.05
    apy
    0.05
     final
    0.05
     salvage
    0.05
    final
    0.05
    Activations Density 0.020%

    No Known Activations