© 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. 69993
    Prev
    Next
    INDEX
    Explanations

    titles and formatting markers typically associated with academic papers

    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
    structuring
    -0.07
    elic
    -0.07
    reo
    -0.07
     onData
    -0.07
     requester
    -0.06
    xae
    -0.06
    aving
    -0.06
    fet
    -0.06
    ourd
    -0.06
    istra
    -0.06
    POSITIVE LOGITS
    uml
    0.06
    Salir
    0.06
    Subsystem
    0.06
    OperationException
    0.06
    ãĥ³ãĥķ
    0.06
    çİĦ
    0.06
     Buccane
    0.05
    OMIC
    0.05
     abandonment
    0.05
     collected
    0.05
    Activations Density 0.001%

    No Known Activations