© 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. 83161
    Prev
    Next
    INDEX
    Explanations

    phrases related to job opportunities and purchasing interests

    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
    edl
    -0.07
    %f
    -0.07
    AndWait
    -0.07
    æĪ²
    -0.07
    adele
    -0.07
    ByExample
    -0.07
    人人
    -0.07
    oeff
    -0.07
    ắng
    -0.07
    velle
    -0.06
    POSITIVE LOGITS
     preferably
    0.07
    etat
    0.06
     interested
    0.06
     anywhere
    0.06
     iota
    0.06
     saya
    0.06
     steady
    0.06
     someone
    0.06
    lop
    0.05
     Exposure
    0.05
    Activations Density 0.011%

    No Known Activations