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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104460
    Prev
    Next
    INDEX
    Explanations

    references to job transfers, accountability, and employment 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
    ILI
    -0.07
    æŁĵ
    -0.07
    achi
    -0.07
    SizePolicy
    -0.07
    λÎŃ
    -0.07
    à¹īà¹ģà¸ģ
    -0.06
    ç´
    -0.06
     ÙħØ«
    -0.06
    ardon
    -0.06
    Äĵ
    -0.06
    POSITIVE LOGITS
     lateral
    0.08
     dem
    0.08
    desk
    0.06
     cub
    0.06
     instead
    0.06
     assignment
    0.06
     retirement
    0.06
    Cast
    0.06
    assign
    0.06
    TRL
    0.06
    Activations Density 0.004%

    No Known Activations