© 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 EvalsExportsinterp-engineNEWAPI 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. 121148
    Prev
    Next
    INDEX
    Explanations

    references to music charts and their rankings

    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
    rique
    -0.07
    å¹³æĪIJ
    -0.07
    ique
    -0.06
    ãĤıãģŁãģĹ
    -0.06
    _rewrite
    -0.06
    ä»ĺ
    -0.06
    Ïİ
    -0.06
    .ct
    -0.06
    åĸľ
    -0.06
    åħ·
    -0.06
    POSITIVE LOGITS
    infeld
    0.06
    qh
    0.06
     gotten
    0.06
     zwar
    0.06
    .online
    0.06
    ufen
    0.06
     iov
    0.06
    udic
    0.06
     intoler
    0.06
    fen
    0.05
    Activations Density 0.002%

    No Known Activations