© 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. 87766
    Prev
    Next
    INDEX
    Explanations

    themes related to privacy and public sharing

    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
    èĩ´
    -0.07
     Genuine
    -0.06
    ÙıÙĨ
    -0.06
    enberg
    -0.06
    enses
    -0.06
     genuine
    -0.06
    716
    -0.06
    ìĦ¸ëĮĢ
    -0.06
    ived
    -0.06
    isky
    -0.06
    POSITIVE LOGITS
     public
    0.09
    æ°¸ä¹ħ
    0.08
     PUBLIC
    0.08
     potentially
    0.07
     perman
    0.07
    -public
    0.07
     Public
    0.07
     permanent
    0.07
    public
    0.07
    ozilla
    0.07
    Activations Density 0.011%

    No Known Activations