© 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. 14539
    Prev
    Next
    INDEX
    Explanations

    references to events and their associated conditions or statuses

    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
    Ïĩε
    -0.07
     interv
    -0.07
    abal
    -0.07
    Ðĩ
    -0.06
    mlink
    -0.06
     bal
    -0.06
     pym
    -0.06
    miner
    -0.06
    rollo
    -0.06
    xCD
    -0.06
    POSITIVE LOGITS
     absence
    0.14
     missing
    0.12
     lack
    0.11
    missing
    0.09
     lacking
    0.09
     missed
    0.08
    Missing
    0.08
     absent
    0.08
    lack
    0.08
     empty
    0.08
    Activations Density 0.088%

    No Known Activations