© 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. 57070
    Prev
    Next
    INDEX
    Explanations

    references to awareness months and related events

    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
    Mock
    -0.07
    ough
    -0.06
    adow
    -0.06
     Mock
    -0.06
     CHRIST
    -0.06
    Christmas
    -0.06
    ifen
    -0.06
    .intellij
    -0.06
    ardi
    -0.06
    icum
    -0.06
    POSITIVE LOGITS
     awareness
    0.08
     Month
    0.08
    #
    0.08
     Week
    0.08
    ãĥ©ãĤ¤ãĥ³
    0.08
     week
    0.07
     month
    0.07
     National
    0.07
    .World
    0.07
    #:
    0.07
    Activations Density 0.044%

    No Known Activations