© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56494
    Prev
    Next
    INDEX
    Explanations

    important noun phrases emphasizing foundational concepts and theorems in a mathematical context

    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
     derivation
    -0.07
     Rosenberg
    -0.06
     Ross
    -0.06
    prd
    -0.06
     Insurance
    -0.06
    .fig
    -0.06
    hiro
    -0.06
    vette
    -0.06
     Ton
    -0.06
     Pres
    -0.06
    POSITIVE LOGITS
     Blasio
    0.08
    wahl
    0.08
    oret
    0.08
    agara
    0.07
    InParameter
    0.07
     reader
    0.07
    iola
    0.07
    elerik
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    AlmostEqual
    0.07
    Activations Density 0.097%

    No Known Activations