© 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. 71302
    Prev
    Next
    INDEX
    Explanations

    activities related to acting and performance training

    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
    anian
    -0.08
    eatures
    -0.08
    habi
    -0.08
    avir
    -0.07
    outh
    -0.07
     mile
    -0.07
    mile
    -0.07
    amil
    -0.07
    éªĮè¯ģçłģ
    -0.07
    avl
    -0.07
    POSITIVE LOGITS
     circulation
    0.06
     circulating
    0.06
     pairwise
    0.06
     confidential
    0.06
     name
    0.06
     Rum
    0.06
     randomly
    0.06
     pairs
    0.06
     choose
    0.05
    ç«Ļ
    0.05
    Activations Density 0.027%

    No Known Activations