© 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. 94180
    Prev
    Next
    INDEX
    Explanations

    references to legal and bureaucratic documentation processes

    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
    lal
    -0.07
    eldon
    -0.07
    allet
    -0.07
    |#
    -0.07
     Dön
    -0.07
    รรà¸Ħ
    -0.06
    Inventory
    -0.06
    apes
    -0.06
     Inventory
    -0.06
    λÏī
    -0.06
    POSITIVE LOGITS
     job
    0.06
    ospace
    0.06
     participating
    0.06
     housing
    0.06
    633
    0.06
     employment
    0.06
     ATT
    0.06
     certain
    0.06
     drug
    0.06
     Bias
    0.06
    Activations Density 0.021%

    No Known Activations