© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal affiliations and organizational roles

    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
    åľĭéļĽ
    -0.07
     international
    -0.07
    abal
    -0.06
     kaps
    -0.06
     abroad
    -0.06
    ÏĦεÏģ
    -0.06
    ono
    -0.06
    Thickness
    -0.06
     afr
    -0.06
    653
    -0.06
    POSITIVE LOGITS
     Regional
    0.12
    Regional
    0.11
     regional
    0.10
     Region
    0.10
     REGION
    0.09
    Region
    0.09
     region
    0.08
    region
    0.08
    (region
    0.08
    .region
    0.07
    Activations Density 0.046%

    No Known Activations