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. 11449
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or categories

    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
     NCAA
    -0.06
     HVAC
    -0.06
     COVID
    -0.06
     FEMA
    -0.05
    .proc
    -0.05
     Kavanaugh
    -0.05
     SOP
    -0.05
     EPA
    -0.05
     Siri
    -0.05
     BBQ
    -0.05
    POSITIVE LOGITS
     UNIVERS
    0.10
     Universal
    0.09
     Baby
    0.09
    baby
    0.09
     univers
    0.09
     British
    0.09
    heritance
    0.08
     universal
    0.08
     inheritance
    0.08
    Baby
    0.08
    Activations Density 0.002%

    No Known Activations