© 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. 81624
    Prev
    Next
    INDEX
    Explanations

    references to historic space missions and their lessons

    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
     uniform
    -0.07
    roperties
    -0.07
    pike
    -0.06
     Uniform
    -0.06
     patrol
    -0.06
    onis
    -0.06
    roti
    -0.06
     former
    -0.06
    mî
    -0.06
    aan
    -0.06
    POSITIVE LOGITS
     Abort
    0.08
    ]={↵
    0.07
    cock
    0.06
     nominal
    0.06
     commanded
    0.06
     Slave
    0.06
    ì¢ħ
    0.06
     Hunts
    0.06
    christ
    0.06
     Cock
    0.06
    Activations Density 0.005%

    No Known Activations