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. 11518
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that represent special or heightened emotional or aesthetic qualities

    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
     Chore
    -0.09
     danced
    -0.09
     chore
    -0.09
     dance
    -0.09
     dances
    -0.09
    dance
    -0.09
     Dance
    -0.08
     dancing
    -0.08
     Sing
    -0.07
     ballet
    -0.07
    POSITIVE LOGITS
     guit
    0.13
     guitar
    0.12
     shredd
    0.11
     Guitar
    0.11
     guitarist
    0.11
     shred
    0.10
     gear
    0.10
     guitars
    0.10
     Gibson
    0.10
    ãĤ®
    0.10
    Activations Density 0.003%

    No Known Activations