© 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. 17-LLAMASCOPE-RES-131K
    11. 130135
    Prev
    Next
    INDEX
    Explanations

    legal and administrative terminology related to regulations, removals, and documentation

    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
    çĦ¶
    -0.07
    isa
    -0.07
    nants
    -0.06
    jid
    -0.06
    mana
    -0.06
    'na
    -0.06
    reira
    -0.06
    errupt
    -0.06
    eger
    -0.06
     âķ
    -0.06
    POSITIVE LOGITS
     anytime
    0.11
     if
    0.10
     depending
    0.09
    if
    0.08
     nếu
    0.08
     jika
    0.08
     sometimes
    0.08
     whenever
    0.08
     إذا
    0.07
     ÑıкÑīо
    0.07
    Activations Density 0.024%

    No Known Activations