© 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. 118976
    Prev
    Next
    INDEX
    Explanations

    concepts related to employment and job market dynamics

    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
    icode
    -0.08
    #ab
    -0.08
    ogne
    -0.07
    çĸ
    -0.07
    @js
    -0.07
    óng
    -0.07
    ogene
    -0.07
     ÐĹаконÑĥ
    -0.07
    ogenesis
    -0.07
    avar
    -0.07
    POSITIVE LOGITS
     skills
    0.06
     sorts
    0.05
     AI
    0.05
    ää
    0.05
     jobs
    0.05
     tasks
    0.05
    amber
    0.05
    iggins
    0.05
    ihad
    0.05
    encer
    0.05
    Activations Density 0.002%

    No Known Activations