© 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. 55285
    Prev
    Next
    INDEX
    Explanations

    references to licensing and attribution in a legal or creative commons context

    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
    ãĥ¼ãĥĨãĤ£
    -0.07
    cura
    -0.06
    ç¨
    -0.06
    aran
    -0.06
    elier
    -0.06
    .subplots
    -0.06
    olf
    -0.06
    ADR
    -0.06
    æ
    -0.06
     refriger
    -0.06
    POSITIVE LOGITS
     copyright
    0.16
     license
    0.15
     Copyright
    0.14
    Copyright
    0.14
     licence
    0.14
    creativecommons
    0.13
     License
    0.13
     copyrights
    0.13
    -license
    0.13
    copyright
    0.13
    Activations Density 0.425%

    No Known Activations