© 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. 15-LLAMASCOPE-RES-131K
    11. 89408
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of key phrases or concepts within a text

    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
    /*č↵
    -0.09
    imbus
    -0.09
    //{{
    -0.09
    acades
    -0.08
    #__
    -0.08
    eyse
    -0.08
    alte
    -0.08
    ãĥ¬ãĤ¹
    -0.08
    Äįan
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    POSITIVE LOGITS
    lessly
    0.08
    ologically
    0.06
    idor
    0.06
    ong
    0.06
    -tabs
    0.06
    Łèĥ½
    0.06
     Hague
    0.06
    gorithm
    0.06
    ym
    0.05
    eration
    0.05
    Activations Density 0.488%

    No Known Activations