Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44186
    Prev
    Next
    INDEX
    Explanations

    syntax elements such as punctuation marks and brackets in code or structured text

    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
    605
    -0.07
    609
    -0.07
    uste
    -0.07
    ër
    -0.07
    =<?=
    -0.07
     imm
    -0.06
    PropertyChanged
    -0.06
    å¹¹
    -0.06
     prat
    -0.06
     compat
    -0.06
    POSITIVE LOGITS
             
    0.19
    ³³³³³³³³³
    0.10
    ----------
    0.09
               
    0.08
    ãĢĢãĢĢãĢĢ ãĢĢ
    0.08
    		 
    0.08
    	 
    0.07
    204
    0.07
     ãĢĢ ãĢĢ ãĢĢ
    0.07
    ----------↵↵
    0.07
    Activations Density 0.023%

    No Known Activations