© 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. 85357
    Prev
    Next
    INDEX
    Explanations

    references to the month of August

    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
    itional
    -0.08
     winters
    -0.07
    uther
    -0.07
    heten
    -0.07
    ationally
    -0.06
    rd
    -0.06
     Ferd
    -0.06
    uled
    -0.06
     Winter
    -0.06
    سÙĪب
    -0.06
    POSITIVE LOGITS
    sburg
    0.09
    eenth
    0.08
    IES
    0.08
    t
    0.08
    mented
    0.07
    enberg
    0.07
    ies
    0.07
    份
    0.07
    oyer
    0.07
    tif
    0.07
    Activations Density 0.034%

    No Known Activations