© 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. 124526
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmaceutical compositions and methods of extraction

    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
    ainties
    -0.07
    flen
    -0.06
    rego
    -0.06
    linger
    -0.06
    irsch
    -0.06
    eger
    -0.06
    obel
    -0.06
    اءات
    -0.06
    obe
    -0.06
    ubre
    -0.06
    POSITIVE LOGITS
    CLUDED
    0.07
     EITHER
    0.06
    stable
    0.06
    :<?
    0.06
    pta
    0.06
     instability
    0.06
    .xtext
    0.06
    wert
    0.06
     mole
    0.06
    ipc
    0.06
    Activations Density 0.017%

    No Known Activations