© 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. 79574
    Prev
    Next
    INDEX
    Explanations

    discussions around market trends and corrections

    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
     permanently
    -0.07
    ungan
    -0.07
     waived
    -0.06
     thaw
    -0.06
     permanent
    -0.06
     displ
    -0.06
     SKIP
    -0.06
     leaps
    -0.06
     bulls
    -0.06
     positively
    -0.06
    POSITIVE LOGITS
     cooling
    0.09
     cooled
    0.08
    cool
    0.08
     Cooling
    0.07
     backlash
    0.07
     slowdown
    0.07
     cooler
    0.07
     cooldown
    0.07
    oga
    0.07
     moderation
    0.07
    Activations Density 0.035%

    No Known Activations