© 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 EvalsExportsAPI 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. 106235
    Prev
    Next
    INDEX
    Explanations

    references to file structures and programming-related details

    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
    scala
    -0.06
    igan
    -0.06
    дн
    -0.06
    209
    -0.06
    velope
    -0.05
    ater
    -0.05
     Silva
    -0.05
    silver
    -0.05
     Andy
    -0.05
    sil
    -0.05
    POSITIVE LOGITS
     EntryPoint
    0.08
     UIResponder
    0.07
    uego
    0.07
     Bund
    0.07
    /owl
    0.07
     chó
    0.07
    YPRE
    0.07
    åħ¥åı£
    0.07
    /favicon
    0.07
     Hers
    0.07
    Activations Density 0.005%

    No Known Activations