© 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. 40066
    Prev
    Next
    INDEX
    Explanations

    phrases related to pricing and government procurement policies

    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
    .userInteractionEnabled
    -0.08
     {?>↵
    -0.08
    vfs
    -0.08
    ãĤĪãģĨãģ§ãģĻ
    -0.07
    OTAL
    -0.07
    ormsg
    -0.07
    iá»ģm
    -0.07
    dÃŃ
    -0.07
    аÑĢÑĸ
    -0.07
     ;č↵
    -0.07
    POSITIVE LOGITS
     if
    0.07
     so
    0.07
     basically
    0.07
     —
    0.07
     usually
    0.07
    ,
    0.06
     meaning
    0.06
     chief
    0.06
     instead
    0.06
     So
    0.06
    Activations Density 0.031%

    No Known Activations