© 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. 70174
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and online presence

    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
    ngo
    -0.06
    iosa
    -0.06
     raw
    -0.06
    rire
    -0.06
    acer
    -0.06
    luet
    -0.06
    arih
    -0.06
    lu
    -0.06
    agn
    -0.06
     èŃ
    -0.06
    POSITIVE LOGITS
     site
    0.07
     premises
    0.07
    ucchini
    0.07
     ì±Ħ
    0.06
    PRETTY
    0.06
    icari
    0.06
     mesmo
    0.06
    URRENT
    0.06
    pot
    0.06
    zent
    0.06
    Activations Density 0.034%

    No Known Activations