© 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. 17-LLAMASCOPE-RES-131K
    11. 84842
    Prev
    Next
    INDEX
    Explanations

    elements related to governance and decision-making in an organizational context

    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
    ãģµ
    -0.06
    entries
    -0.06
    roat
    -0.06
    _backend
    -0.06
    _STATES
    -0.06
    ONO
    -0.06
    Å¡ka
    -0.06
    _frontend
    -0.06
     Harvard
    -0.05
     Entries
    -0.05
    POSITIVE LOGITS
    enate
    0.08
    Prov
    0.08
    igel
    0.07
     Prov
    0.07
    pector
    0.07
     Sabb
    0.07
    ilon
    0.07
    ’ÑıÑĤ
    0.07
    ulty
    0.07
     Gül
    0.07
    Activations Density 0.004%

    No Known Activations