© 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 EvalsExportsinterp-engineNEWAPI 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. 98569
    Prev
    Next
    INDEX
    Explanations

    terms related to government funding and educational resources in the context of the pandemic

    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
    cka
    -0.07
     Sil
    -0.06
    ctl
    -0.06
     disc
    -0.06
     Ibrahim
    -0.06
     Griffith
    -0.06
    reh
    -0.06
    bot
    -0.06
    osen
    -0.06
    cep
    -0.06
    POSITIVE LOGITS
    à¸ī
    0.06
    linger
    0.06
    ãĥĹãĥ¬
    0.06
    .fi
    0.06
    ufig
    0.06
    iard
    0.06
    âķ
    0.06
    à¸µà¸ľ
    0.06
     fat
    0.06
     ÑĤол
    0.06
    Activations Density 0.113%

    No Known Activations