© 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. 22-LLAMASCOPE-RES-131K
    11. 4132
    Prev
    Next
    INDEX
    Explanations

    the word "only" and related phrases indicating exclusivity or uniqueness

    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
     already
    -0.08
     Already
    -0.08
    already
    -0.08
    asar
    -0.07
    avic
    -0.07
     nejen
    -0.07
    ниÑĨÑĥ
    -0.07
    Already
    -0.07
    дон
    -0.07
     Ñĥже
    -0.07
    POSITIVE LOGITS
     really
    0.10
     ever
    0.10
    -ever
    0.09
     truly
    0.09
    Really
    0.08
     REALLY
    0.08
    ãĥ¼ãĤ¹ãĥĪ
    0.08
    羣æŃ£
    0.08
     EVER
    0.08
     interested
    0.07
    Activations Density 0.021%

    No Known Activations