© 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. 9-LLAMASCOPE-RES-131K
    11. 95864
    Prev
    Next
    INDEX
    Explanations

    references to academic degrees or classification systems

    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
     αÏħÏĦά
    -0.07
    oop
    -0.06
    inker
    -0.06
    inho
    -0.06
    lder
    -0.06
    lag
    -0.06
    IED
    -0.05
    ÑĥÑĩ
    -0.05
    owski
    -0.05
    .libs
    -0.05
    POSITIVE LOGITS
    ê²
    0.07
    ÂłPS
    0.07
    Cpp
    0.07
    ÐĶÐļ
    0.06
    ÑĢава
    0.06
    ijn
    0.06
    ulty
    0.06
    érique
    0.06
     Sesso
    0.06
    .GetString
    0.06
    Activations Density 0.001%

    No Known Activations