© 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. 15-LLAMASCOPE-RES-131K
    6. 90491
    Prev
    Next
    INDEX
    Explanations

    frequent instances of the word "known" in various contexts

    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
    кÑĥлÑĮ
    -0.06
    ime
    -0.06
    orsche
    -0.06
    ifornia
    -0.06
     slugg
    -0.06
     Sous
    -0.06
    amiento
    -0.06
    ats
    -0.05
    od
    -0.05
    dl
    -0.05
    POSITIVE LOGITS
    rani
    0.08
    KER
    0.07
     dai
    0.06
    _ai
    0.06
    UTH
    0.06
    apse
    0.06
    unik
    0.06
    -bot
    0.06
    AdapterManager
    0.06
     among
    0.06
    Activations Density 0.011%

    No Known Activations