© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    phrases related to transportation, work, and living conditions

    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
    ingroup
    -0.07
    memberof
    -0.07
    à¤Ĥध
    -0.06
    ieri
    -0.06
    ±
    -0.06
     stabil
    -0.06
    ycled
    -0.06
    едÑĮ
    -0.06
    icot
    -0.06
    âĶĺ
    -0.06
    POSITIVE LOGITS
     visit
    0.09
     access
    0.08
     visiting
    0.08
     Access
    0.07
     job
    0.07
     attending
    0.07
     accessing
    0.07
     Job
    0.07
    visit
    0.07
     employment
    0.07
    Activations Density 0.013%

    No Known Activations