© 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. 83555
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and their monetary 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
     Sept
    -0.07
    uem
    -0.07
     July
    -0.07
    ews
    -0.06
     September
    -0.06
     October
    -0.06
     March
    -0.06
     June
    -0.06
    adelphia
    -0.05
    alling
    -0.05
    POSITIVE LOGITS
    _ioctl
    0.08
    ï¼»
    0.08
    orig
    0.08
    aver
    0.08
    owitz
    0.07
    اص
    0.07
    ést
    0.07
    пп
    0.07
    Ø¡
    0.07
    izont
    0.07
    Activations Density 0.051%

    No Known Activations