© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    references to rivers and water-related activities

    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
     spiral
    -0.07
     impover
    -0.06
     Tune
    -0.06
    .setOutput
    -0.06
     Outside
    -0.06
     outside
    -0.06
     pare
    -0.06
    ä¸ĺ
    -0.06
    NSS
    -0.06
    âĸ¡
    -0.06
    POSITIVE LOGITS
     bridges
    0.12
     bridge
    0.12
     crossing
    0.11
     crossings
    0.11
    bridge
    0.10
     Bridges
    0.10
     Bridge
    0.10
     ford
    0.10
     brid
    0.10
    -cross
    0.10
    Activations Density 0.032%

    No Known Activations