© 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. 86876
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and administrative services

    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
    ureau
    -0.08
    >Lorem
    -0.08
    erg
    -0.08
    ｡
    -0.08
    achment
    -0.08
    âĢ¦âĢ¦ãĢĤ
    -0.07
    åĦĢ
    -0.07
    ÏĩεδÏĮν
    -0.07
    ickest
    -0.07
    REATE
    -0.07
    POSITIVE LOGITS
     Fel
    0.06
     |
    0.06
     Bien
    0.06
    [email
    0.05
    ter
    0.05
     Tun
    0.05
    |int
    0.05
    amps
    0.05
     Gam
    0.05
    iÄįe
    0.05
    Activations Density 0.044%

    No Known Activations