© 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. 75574
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to trademarks

    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
    odes
    -0.08
    ISA
    -0.07
    oday
    -0.07
    oda
    -0.07
    AEA
    -0.07
    å½¹
    -0.07
    otech
    -0.07
    ourn
    -0.07
    idades
    -0.07
    bane
    -0.07
    POSITIVE LOGITS
    ed
    0.11
    eting
    0.08
     holders
    0.08
    ing
    0.08
     infringement
    0.07
    utzer
    0.07
    able
    0.07
    edn
    0.07
    edl
    0.07
    itionally
    0.07
    Activations Density 0.002%

    No Known Activations