© 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. 86701
    Prev
    Next
    INDEX
    Explanations

    mentions of popular social media platforms and digital services

    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
     McCabe
    -0.07
    aka
    -0.06
    usc
    -0.06
    omor
    -0.06
     aka
    -0.06
     Jerome
    -0.06
    est
    -0.06
    uen
    -0.06
    лÑĥж
    -0.06
    ifi
    -0.06
    POSITIVE LOGITS
    /WebAPI
    0.09
    ®,
    0.08
    ®
    0.08
    umbn
    0.07
    orners
    0.07
    .gov
    0.07
    -esque
    0.07
     etc
    0.07
    -logo
    0.07
     trap
    0.07
    Activations Density 0.033%

    No Known Activations