© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90173
    Prev
    Next
    INDEX
    Explanations

    concepts related to equilibrium and stability in complex systems

    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
     Obl
    -0.06
    alist
    -0.06
    asia
    -0.06
    hn
    -0.05
    emer
    -0.05
    OB
    -0.05
     mechanic
    -0.05
    zel
    -0.05
    Mapping
    -0.05
    emek
    -0.05
    POSITIVE LOGITS
    ottie
    0.09
    reo
    0.08
     equilibrium
    0.08
    acon
    0.07
    wner
    0.07
    indrome
    0.07
    ุà¸ķ
    0.07
    uten
    0.07
    argo
    0.07
    çĬ¶æħĭ
    0.07
    Activations Density 0.028%

    No Known Activations