© 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. 89987
    Prev
    Next
    INDEX
    Explanations

    references to automotive features and specifications

    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
    μιÏĥ
    -0.07
    asio
    -0.06
    malink
    -0.06
    SSERT
    -0.06
    paralleled
    -0.06
    SWG
    -0.06
    odie
    -0.06
    assa
    -0.06
    alam
    -0.06
    berger
    -0.06
    POSITIVE LOGITS
     Til
    0.07
    ë´ī
    0.07
    Як
    0.06
    对æĸ¹
    0.06
    least
    0.06
    utral
    0.06
    Models
    0.06
    Ä°N
    0.06
    model
    0.06
    poser
    0.06
    Activations Density 0.007%

    No Known Activations