© 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. 120310
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure in the document

    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
    ambre
    -0.06
    ard
    -0.06
    omat
    -0.06
     Poke
    -0.06
     compr
    -0.06
    erve
    -0.06
    erp
    -0.06
    ilar
    -0.06
    enheim
    -0.06
     r
    -0.05
    POSITIVE LOGITS
    leground
    0.07
    COD
    0.07
    wake
    0.07
    SGlobal
    0.07
    script
    0.07
    arem
    0.07
    icode
    0.07
     Miles
    0.06
     cod
    0.06
    imenti
    0.06
    Activations Density 0.016%

    No Known Activations