© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74486
    Prev
    Next
    INDEX
    Explanations

    phrases with complex compound sentences and conjunctions

    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
    itz
    -0.07
    .INSTANCE
    -0.06
    ŀ
    -0.06
     EGL
    -0.06
    ãĤĪãģĨãģ«
    -0.06
    .foreach
    -0.06
    =======
    -0.06
    etti
    -0.06
    _PENDING
    -0.06
    κÎŃ
    -0.06
    POSITIVE LOGITS
    alore
    0.06
    atron
    0.06
    ingham
    0.06
    037
    0.06
     Walton
    0.06
    787
    0.06
    ÑģÑĤÑĢа
    0.06
    mdb
    0.06
    ropy
    0.06
    emean
    0.06
    Activations Density 0.118%

    No Known Activations