© 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. 125935
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high levels of emotion or drama

    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
    istrovstvÃŃ
    -0.08
     ryb
    -0.07
    copies
    -0.07
    Composite
    -0.07
    monic
    -0.07
    ISCO
    -0.06
    erse
    -0.06
    uish
    -0.06
    andin
    -0.06
    BuilderFactory
    -0.06
    POSITIVE LOGITS
     said
    0.06
     former
    0.06
    ecz
    0.06
    498
    0.06
    .SYSTEM
    0.06
     atIndex
    0.06
     study
    0.06
     intl
    0.06
     says
    0.06
    enk
    0.06
    Activations Density 0.005%

    No Known Activations