© 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. 5-LLAMASCOPE-RES-131K
    11. 127017
    Prev
    Next
    INDEX
    Explanations

    references to specific articles or reports

    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
    ereo
    -0.07
    edis
    -0.07
    erus
    -0.07
    sep
    -0.06
     нак
    -0.06
    541
    -0.06
    acea
    -0.06
    nt
    -0.06
    ļĮ
    -0.06
    ãĤ¦ãĤ¹
    -0.06
    POSITIVE LOGITS
    æĹıèĩªæ²»
    0.07
     Squad
    0.06
    TEGER
    0.06
     Feinstein
    0.06
     jumper
    0.06
     Sle
    0.06
    stakes
    0.06
     Hint
    0.06
     Leone
    0.06
    zych
    0.06
    Activations Density 0.000%

    No Known Activations