© 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. 79230
    Prev
    Next
    INDEX
    Explanations

    code-related terms indicating data validation and requirements

    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
    again
    -0.07
    /pg
    -0.06
     again
    -0.06
    idi
    -0.06
    .mixin
    -0.06
    andi
    -0.06
    .dex
    -0.06
     newInstance
    -0.06
     Gins
    -0.06
    isia
    -0.06
    POSITIVE LOGITS
    (optional
    0.07
    orado
    0.07
     optional
    0.07
    kehr
    0.07
    keh
    0.06
    hoa
    0.06
    mour
    0.06
    oeff
    0.06
    egie
    0.06
    strand
    0.06
    Activations Density 0.007%

    No Known Activations