© 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. 124701
    Prev
    Next
    INDEX
    Explanations

    text related to terms and conditions or disclaimers

    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
    lot
    -0.07
    unger
    -0.07
    kes
    -0.07
     caption
    -0.06
     GObject
    -0.06
    zia
    -0.06
    leton
    -0.06
     célib
    -0.06
     burn
    -0.06
    readcr
    -0.06
    POSITIVE LOGITS
    leck
    0.07
    OKIE
    0.07
    lez
    0.06
    WEEN
    0.06
    /ay
    0.06
    ray
    0.06
    0.06
     bour
    0.06
    /bower
    0.06
     lorem
    0.06
    Activations Density 0.003%

    No Known Activations