© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the" as a marker

    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
     hed
    -0.07
     
    -0.06
     Bang
    -0.06
    мÑı
    -0.06
     cáo
    -0.06
    ãĥĨãĥ«
    -0.06
    allet
    -0.06
     оÑģновном
    -0.06
    üstü
    -0.06
    omentum
    -0.06
    POSITIVE LOGITS
    pta
    0.09
     presence
    0.09
    eos
    0.07
    etine
    0.07
     absence
    0.07
    ÃŃÅĻ
    0.07
     combination
    0.06
     inability
    0.06
     broad
    0.06
    presence
    0.06
    Activations Density 0.040%

    No Known Activations