© 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. 74542
    Prev
    Next
    INDEX
    Explanations

    references to organization and leadership dynamics

    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
    covers
    -0.07
    PÅĻed
    -0.07
    occo
    -0.07
     صاØŃب
    -0.07
    Vý
    -0.07
     Shade
    -0.07
    ezier
    -0.07
    _drv
    -0.07
    tember
    -0.07
    åij³
    -0.07
    POSITIVE LOGITS
     themselves
    0.08
    ioned
    0.08
    innen
    0.07
    arto
    0.06
    wick
    0.06
    875
    0.06
    ugar
    0.06
    inger
    0.06
     Moh
    0.06
    ulty
    0.05
    Activations Density 0.051%

    No Known Activations