© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73716
    Prev
    Next
    INDEX
    Explanations

    topics related to space exploration and the involvement of private companies in that sector

    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
    idl
    -0.08
    _distribution
    -0.07
    ahl
    -0.07
     Affero
    -0.07
    xD
    -0.07
    eba
    -0.07
    prene
    -0.06
    éIJĺ
    -0.06
     McLaren
    -0.06
     Merlin
    -0.06
    POSITIVE LOGITS
     missions
    0.08
     Earth
    0.07
     Launcher
    0.07
     funding
    0.07
     budget
    0.06
    Scaled
    0.06
    Reusable
    0.06
     hala
    0.06
     manned
    0.06
    gewater
    0.06
    Activations Density 0.005%

    No Known Activations