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. 11515
    Prev
    Next
    INDEX
    Explanations

    specific coded or technical identifiers, particularly related to computer programming and serial communication

    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
     –
    -0.09
     --
    -0.09
     tasked
    -0.08
    Humans
    -0.07
     Narendra
    -0.07
    \"
    -0.07
     Crafting
    -0.07
     transitioning
    -0.06
    ekil
    -0.06
     dataset
    -0.06
    POSITIVE LOGITS
     Dublin
    0.10
     Irish
    0.09
     Picasso
    0.09
     Paris
    0.09
     Quinn
    0.08
     Pound
    0.08
     avant
    0.08
     Ireland
    0.08
     American
    0.07
     Joyce
    0.07
    Activations Density 0.003%

    No Known Activations