© 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. 15-LLAMASCOPE-RES-131K
    11. 87281
    Prev
    Next
    INDEX
    Explanations

    phrases related to women's rights and social changes

    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
    ulary
    -0.08
    eca
    -0.07
    aml
    -0.07
    chio
    -0.07
    ederland
    -0.07
    ventus
    -0.07
    innamon
    -0.07
    ROUGH
    -0.07
    ddit
    -0.07
    vide
    -0.07
    POSITIVE LOGITS
    sten
    0.07
    191
    0.06
     industrial
    0.06
    Jim
    0.06
     urban
    0.06
    XP
    0.06
    667
    0.06
    660
    0.06
     Jim
    0.06
    194
    0.06
    Activations Density 0.002%

    No Known Activations