© 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. 72546
    Prev
    Next
    INDEX
    Explanations

    career opportunities and pathways in various fields

    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
     cuc
    -0.07
     Dodd
    -0.07
     stupid
    -0.06
     Profession
    -0.06
    irsch
    -0.06
    ny
    -0.06
    aries
    -0.06
    athan
    -0.06
     mos
    -0.06
    mirror
    -0.06
    POSITIVE LOGITS
    opup
    0.10
     eventual
    0.09
     eventually
    0.08
     Eventually
    0.07
     menjadi
    0.07
    Eventually
    0.07
    ClientRect
    0.07
     become
    0.07
     someday
    0.07
     further
    0.07
    Activations Density 0.020%

    No Known Activations