© 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. 15-LLAMASCOPE-RES-131K
    11. 90193
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific disciplines, particularly in the fields of biology and physics

    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
    eldo
    -0.09
    IID
    -0.07
     çĶŁåij½åij¨æľŁåĩ½æķ°
    -0.07
    inç
    -0.07
    ses
    -0.07
    /down
    -0.06
    itis
    -0.06
    ary
    -0.06
    ahrung
    -0.06
    olt
    -0.06
    POSITIVE LOGITS
    /legal
    0.09
    /math
    0.07
    -economic
    0.07
    /ge
    0.06
    /social
    0.06
    -cultural
    0.06
     Lansing
    0.06
    Ñĩки
    0.06
    aight
    0.06
     Warfare
    0.05
    Activations Density 0.081%

    No Known Activations