© 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. 87614
    Prev
    Next
    INDEX
    Explanations

    words related to reproduction and reproduction rights

    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
    monds
    -0.07
    ways
    -0.07
    ley
    -0.07
    earing
    -0.06
     Ye
    -0.06
    ged
    -0.06
    rd
    -0.06
    len
    -0.06
    ipp
    -0.06
    more
    -0.06
    POSITIVE LOGITS
    .dex
    0.08
    mlin
    0.07
    zent
    0.07
    iever
    0.07
    onse
    0.07
    gom
    0.07
    frauen
    0.07
    agues
    0.07
    lush
    0.07
    rieve
    0.07
    Activations Density 0.006%

    No Known Activations