© 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. 78952
    Prev
    Next
    INDEX
    Explanations

    company names and copyright statements

    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
    unden
    -0.07
     Preis
    -0.06
    ekim
    -0.06
    ori
    -0.06
    ilha
    -0.06
    ------+------+
    -0.06
     DIN
    -0.06
    479
    -0.06
    inges
    -0.06
    tons
    -0.06
    POSITIVE LOGITS
    Copyright
    0.07
    hana
    0.07
     impro
    0.07
     Copyright
    0.07
    opyright
    0.07
     Bison
    0.07
     عÙĦ
    0.07
    zier
    0.06
    ëĪĦ
    0.06
    COPY
    0.06
    Activations Density 0.001%

    No Known Activations