© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40047
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and statistics

    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
     Harr
    -0.06
    ocha
    -0.06
     temp
    -0.06
    och
    -0.06
    omic
    -0.06
     Balt
    -0.06
    macen
    -0.05
     Hag
    -0.05
     Land
    -0.05
     DETAILS
    -0.05
    POSITIVE LOGITS
    EFA
    0.08
    Msp
    0.08
    MatrixMode
    0.07
    ì¦Ī
    0.07
    zp
    0.07
    obot
    0.07
    ItemImage
    0.07
     hepat
    0.07
    ÎŃαÏĤ
    0.07
    олÑİ
    0.06
    Activations Density 0.001%

    No Known Activations