© 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. 40004
    Prev
    Next
    INDEX
    Explanations

    special characters or non-standard symbols in the 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
    оказ
    -0.07
    /or
    -0.07
    kest
    -0.07
    otten
    -0.07
    ses
    -0.06
     ddl
    -0.06
    ternet
    -0.06
    Ú¯ÙĬ
    -0.06
    ìłIJ
    -0.06
     wich
    -0.06
    POSITIVE LOGITS
    hoff
    0.07
    489
    0.06
    ensed
    0.06
    vánÃŃ
    0.06
    536
    0.06
    ONENT
    0.06
    ICLE
    0.06
     egret
    0.06
    raquo
    0.06
    izzly
    0.06
    Activations Density 0.008%

    No Known Activations