© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1289
    Prev
    Next
    INDEX
    Explanations

    discussions about trends and performance in music or film

    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
     role
    -0.06
     forever
    -0.06
    owed
    -0.06
     rec
    -0.05
     Rudd
    -0.05
    ilver
    -0.05
    ÄįnÃŃ
    -0.05
    ·
    -0.05
    521
    -0.05
     NEVER
    -0.05
    POSITIVE LOGITS
    æģ¯
    0.07
    platz
    0.07
     trú
    0.07
    ëŀ
    0.07
    linky
    0.07
    нин
    0.07
     Äijá»Ļt
    0.07
    Sparse
    0.07
    urat
    0.07
     omas
    0.07
    Activations Density 0.011%

    No Known Activations