© 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. 5-LLAMASCOPE-RES-131K
    11. 126724
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and administrative processes in government and organizational contexts

    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
     pend
    -0.07
     Pend
    -0.07
    ham
    -0.07
    urse
    -0.07
    avers
    -0.06
    ĵ¨
    -0.06
     dile
    -0.06
    bourg
    -0.06
    _LAT
    -0.06
     INTERN
    -0.06
    POSITIVE LOGITS
    onn
    0.07
    isto
    0.06
    onnen
    0.06
    ursors
    0.06
     Hak
    0.06
     Mans
    0.06
     Hol
    0.06
    ACITY
    0.06
    oulos
    0.05
    inkel
    0.05
    Activations Density 0.255%

    No Known Activations