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. 11470
    Prev
    Next
    INDEX
    Explanations

    references to research topics in oncology, particularly concerning CNS malignancies

    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
     administer
    -0.07
     Psychic
    -0.06
     psychic
    -0.06
    tvrt
    -0.06
    vt
    -0.06
     admin
    -0.05
    ÙĪØ«
    -0.05
    è¦ļ
    -0.05
    atu
    -0.05
    CERT
    -0.05
    POSITIVE LOGITS
     Editors
    0.12
     Editor
    0.12
     Editorial
    0.12
     manuscripts
    0.11
     journal
    0.11
     editorial
    0.10
     editors
    0.10
     readers
    0.10
     editor
    0.10
     manuscript
    0.10
    Activations Density 0.011%

    No Known Activations