© 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. 87716
    Prev
    Next
    INDEX
    Explanations

    specific models and categories of vehicles

    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
    ulen
    -0.07
    ISCO
    -0.07
    istrovstvÃŃ
    -0.07
    alink
    -0.07
    YLON
    -0.07
    untas
    -0.07
    pit
    -0.07
    .scalablytyped
    -0.07
    pliers
    -0.07
    ousel
    -0.07
    POSITIVE LOGITS
    oba
    0.07
    -bodied
    0.07
     model
    0.07
    lÃŃ
    0.06
     Sed
    0.06
    رخ
    0.06
     Sport
    0.06
     models
    0.06
    -series
    0.06
    model
    0.06
    Activations Density 0.018%

    No Known Activations