© 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. 83037
    Prev
    Next
    INDEX
    Explanations

    references to the word "Royal" and its variations

    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
    CCR
    -0.07
    ichel
    -0.06
    empor
    -0.06
     Jou
    -0.06
    907
    -0.05
    uddenly
    -0.05
    ITU
    -0.05
    es
    -0.05
    yre
    -0.05
    oman
    -0.05
    POSITIVE LOGITS
    izing
    0.09
    izations
    0.08
    ization
    0.08
    izes
    0.08
    ize
    0.08
    ाà¤ĩ
    0.07
    ised
    0.07
    ton
    0.07
    ized
    0.07
    izar
    0.07
    Activations Density 0.008%

    No Known Activations