© 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. 120035
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements in the document

    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
     Jay
    -0.07
    ined
    -0.06
    ilar
    -0.06
    yr
    -0.06
    561
    -0.06
     Hayward
    -0.06
    tar
    -0.06
    subnet
    -0.06
    insk
    -0.06
     Treasure
    -0.05
    POSITIVE LOGITS
    sizes
    0.07
    osg
    0.07
    adh
    0.07
     cabo
    0.07
    uba
    0.06
    $title
    0.06
    umo
    0.06
    .setTitle
    0.06
     pageTitle
    0.06
     جÙħ
    0.06
    Activations Density 0.005%

    No Known Activations