© 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. 30502
    Prev
    Next
    INDEX
    Explanations

    references to user account details and email communication

    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
    ngen
    -0.08
    inx
    -0.07
    dÃŃ
    -0.07
    abee
    -0.07
    utto
    -0.07
    .defaults
    -0.07
     karak
    -0.07
    ourg
    -0.07
    atform
    -0.06
    ello
    -0.06
    POSITIVE LOGITS
     listed
    0.07
     registered
    0.07
     Registered
    0.06
    ëŁī
    0.06
     Mitch
    0.06
    iska
    0.05
     Moor
    0.05
     Bai
    0.05
    awy
    0.05
     Reyn
    0.05
    Activations Density 0.024%

    No Known Activations