© 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. 15-LLAMASCOPE-RES-131K
    11. 88431
    Prev
    Next
    INDEX
    Explanations

    references to travel routes and options

    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
    igel
    -0.07
    ients
    -0.07
     conc
    -0.06
    âķIJ
    -0.06
     entr
    -0.06
    iese
    -0.06
    ientes
    -0.06
    첨ë¶Ģ
    -0.06
     deep
    -0.06
    azzi
    -0.06
    POSITIVE LOGITS
    .cms
    0.06
    нима
    0.06
    jes
    0.06
    immel
    0.06
    ichel
    0.06
     sprav
    0.06
    лем
    0.06
    bach
    0.06
    orgot
    0.06
    èľ
    0.06
    Activations Density 0.004%

    No Known Activations