© 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. 5-LLAMASCOPE-RES-131K
    11. 126422
    Prev
    Next
    INDEX
    Explanations

    terms related to completion and finalization processes

    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
    tie
    -0.06
     Bund
    -0.06
    een
    -0.06
    Bundle
    -0.06
    147
    -0.06
    /is
    -0.06
    ligt
    -0.06
     preempt
    -0.06
     Becker
    -0.06
    arma
    -0.06
    POSITIVE LOGITS
    mente
    0.10
    clud
    0.08
    Æ¡
    0.08
    arily
    0.07
    quares
    0.07
    olson
    0.07
    rosse
    0.07
    reesome
    0.07
    ured
    0.07
    eway
    0.07
    Activations Density 0.002%

    No Known Activations