© 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. 17-LLAMASCOPE-RES-131K
    11. 78631
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace policies and social guidelines

    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
    åħ¹
    -0.06
    ãģĹãĤĩ
    -0.06
    elah
    -0.06
    LocalizedString
    -0.06
    Unchecked
    -0.06
    IFn
    -0.06
    ä¾
    -0.06
    atories
    -0.06
    andest
    -0.06
    èľ
    -0.06
    POSITIVE LOGITS
    olicy
    0.10
     decision
    0.09
     policy
    0.09
     categorical
    0.08
     rules
    0.07
    Decision
    0.07
    pled
    0.07
     rule
    0.07
     exclus
    0.07
     decisions
    0.07
    Activations Density 0.027%

    No Known Activations