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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89053
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions that indicate relationships in a sentence

    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
    _Tis
    -0.08
    ãĤ¹ãĤ¯
    -0.07
    itect
    -0.07
    eparator
    -0.07
    zept
    -0.06
    pez
    -0.06
    YST
    -0.06
    onda
    -0.06
    aster
    -0.06
    488
    -0.06
    POSITIVE LOGITS
     Bom
    0.06
    essa
    0.06
     âĹĦ
    0.06
     compared
    0.06
    ä¸ĭåİ»
    0.06
     Dyn
    0.06
    .fhir
    0.06
    Backing
    0.06
    Promise
    0.05
    ãĥ¼ãĥª
    0.05
    Activations Density 0.050%

    No Known Activations