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

    Neuronpedia

    Jacobian LensNEW
    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. 131069
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making processes

    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
    çµIJ
    -0.07
    cum
    -0.07
    aupt
    -0.06
    utations
    -0.06
     Hyp
    -0.06
    ÇIJ
    -0.05
    ista
    -0.05
    ToOne
    -0.05
    Attached
    -0.05
    ì§Ģ
    -0.05
    POSITIVE LOGITS
     now
    0.23
     next
    0.22
     ÑĤепеÑĢÑĮ
    0.19
    now
    0.19
     Now
    0.19
    next
    0.18
     Next
    0.18
    Next
    0.17
     NEXT
    0.17
    Now
    0.17
    Activations Density 0.114%

    No Known Activations