© 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. 71212
    Prev
    Next
    INDEX
    Explanations

    mentions of music albums and related details

    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
    ص
    -0.07
    <?↵
    -0.06
    urst
    -0.06
    ãĤ¶
    -0.06
    uzzi
    -0.06
    buz
    -0.06
    txn
    -0.06
    تÛĮ
    -0.06
     Linden
    -0.06
     pop
    -0.06
    POSITIVE LOGITS
    nr
    0.07
    ouver
    0.07
    Nr
    0.07
    iaux
    0.07
    leton
    0.07
    NR
    0.06
    ÙĦÙĬات
    0.06
    ì§ij
    0.06
    _nr
    0.06
    loy
    0.06
    Activations Density 0.023%

    No Known Activations