© 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. 58932
    Prev
    Next
    INDEX
    Explanations

    terms related to antibodies and their role in diagnostics and immunity

    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
    arde
    -0.09
    ATUS
    -0.08
    fak
    -0.07
    abo
    -0.07
    emin
    -0.07
    etto
    -0.07
    ampo
    -0.07
    673
    -0.07
    apur
    -0.07
    æī£
    -0.07
    POSITIVE LOGITS
     Ab
    0.07
     against
    0.07
     Against
    0.07
     raised
    0.06
     Ig
    0.06
    airo
    0.06
     formed
    0.05
    AGMA
    0.05
     tire
    0.05
    ied
    0.05
    Activations Density 0.004%

    No Known Activations