© 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. 107210
    Prev
    Next
    INDEX
    Explanations

    scientific terms and expressions related to particle physics and interactions

    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
     Mess
    -0.08
    Mess
    -0.07
    _blocks
    -0.07
    mess
    -0.07
    achuset
    -0.06
    nob
    -0.06
     slash
    -0.06
    /renderer
    -0.06
     rod
    -0.06
    аниÑĨ
    -0.06
    POSITIVE LOGITS
     exit
    0.07
     trajectories
    0.07
    Rejected
    0.07
     Tra
    0.07
     Exiting
    0.07
     DÃŃky
    0.07
    uggage
    0.07
    utherland
    0.06
    Caught
    0.06
    Exiting
    0.06
    Activations Density 0.032%

    No Known Activations