© 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. 17-LLAMASCOPE-RES-131K
    11. 71282
    Prev
    Next
    INDEX
    Explanations

    references to the name "Milton."

    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
    tÃŃ
    -0.07
    elda
    -0.07
    ATO
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    ãģĨ
    -0.07
    uitka
    -0.06
    igan
    -0.06
    hang
    -0.06
    abi
    -0.06
    oru
    -0.06
    POSITIVE LOGITS
    ium
    0.07
    nier
    0.07
     Keynes
    0.07
    ius
    0.07
    ian
    0.07
     unf
    0.07
    ENTIAL
    0.06
    ÆĴ
    0.06
    iterate
    0.06
    anche
    0.06
    Activations Density 0.002%

    No Known Activations