© 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. 29000
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    aida
    -0.07
    å§ĭ
    -0.07
    μοÏģ
    -0.07
    echa
    -0.06
    oller
    -0.06
    iveau
    -0.06
    icho
    -0.06
    лем
    -0.06
    .grp
    -0.06
    isol
    -0.06
    POSITIVE LOGITS
    andel
    0.07
    MPI
    0.06
    /tos
    0.06
     scrut
    0.06
    essler
    0.06
     Diss
    0.06
     jo
    0.06
     queryInterface
    0.06
    åľ°æĸ¹
    0.06
     dissolve
    0.06
    Activations Density 0.001%

    No Known Activations