© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88021
    Prev
    Next
    INDEX
    Explanations

    specific mentions of legal terms and conditions related to substances

    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
    idl
    -0.07
    ılıç
    -0.07
    /gin
    -0.07
    noinspection
    -0.07
    Å©
    -0.06
    querque
    -0.06
    itzer
    -0.06
    .spin
    -0.06
    cker
    -0.06
    ãģĤãģĴ
    -0.06
    POSITIVE LOGITS
    ζε
    0.07
    ed
    0.07
    iced
    0.07
    CTR
    0.07
    미
    0.07
    egis
    0.07
    arak
    0.07
     edil
    0.07
    ains
    0.06
    dge
    0.06
    Activations Density 0.018%

    No Known Activations