© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82767
    Prev
    Next
    INDEX
    Explanations

    medical or scientific terminology

    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
    vla
    -0.08
    familia
    -0.07
    .bz
    -0.07
    archical
    -0.07
    usch
    -0.06
    _framework
    -0.06
    ansen
    -0.06
    iever
    -0.06
    aub
    -0.06
    hack
    -0.06
    POSITIVE LOGITS
     branch
    0.10
    branch
    0.09
     Branch
    0.09
     discipline
    0.09
    elay
    0.08
     branches
    0.08
    пÑĢиклад
    0.08
    elves
    0.07
    Branch
    0.07
     departments
    0.07
    Activations Density 0.048%

    No Known Activations