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. 22-LLAMASCOPE-RES-131K
    6. 5519
    Prev
    Next
    INDEX
    Explanations

    references to fans and fan-related activities

    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
     Cannes
    -0.06
     arte
    -0.06
     rash
    -0.06
    aviours
    -0.05
    åħ¬å¼Ģ
    -0.05
    ooled
    -0.05
     von
    -0.05
     accession
    -0.05
    .Template
    -0.05
    าà¸Ķ
    -0.05
    POSITIVE LOGITS
     zápas
    0.07
    fans
    0.07
    apos
    0.07
    .tk
    0.07
     Fans
    0.07
     stew
    0.07
    Fans
    0.07
    ucas
    0.07
    OUNTER
    0.07
    ramework
    0.07
    Activations Density 0.006%

    No Known Activations