© 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. 117433
    Prev
    Next
    INDEX
    Explanations

    the word "por" and its variations, indicating mentions of causes or reasons

    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
    ustil
    -0.08
    thinkable
    -0.07
    .CustomButton
    -0.07
    вад
    -0.07
    endencies
    -0.07
    λια
    -0.07
    okoj
    -0.07
    gnore
    -0.07
    _softc
    -0.07
    ocaly
    -0.07
    POSITIVE LOGITS
    ras
    0.07
     sake
    0.07
     means
    0.07
    ogh
    0.07
    ance
    0.06
    oth
    0.06
    ĭ
    0.06
    centaje
    0.06
    ages
    0.06
     courtesy
    0.06
    Activations Density 0.006%

    No Known Activations