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. 44094
    Prev
    Next
    INDEX
    Explanations

    structural elements and academic components in a thesis or scholarly paper

    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
     stretch
    -0.06
    *)"
    -0.06
    uluk
    -0.06
    grund
    -0.06
     bundle
    -0.06
     classes
    -0.05
    Bundle
    -0.05
     lunch
    -0.05
    stretch
    -0.05
    ìħĢ
    -0.05
    POSITIVE LOGITS
     Thesis
    0.14
     thesis
    0.13
     Dissertation
    0.12
     Degree
    0.11
    Advisor
    0.11
    .degree
    0.10
     Supervisor
    0.10
    Degree
    0.10
    .abstract
    0.10
    thesis
    0.10
    Activations Density 0.004%

    No Known Activations