© 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. 106199
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific terminology, specifically those involving biological or biochemical processes

    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
    ed
    -0.09
    edo
    -0.08
    elyn
    -0.07
    elder
    -0.07
    undry
    -0.07
    ersen
    -0.07
    allen
    -0.07
    ãĥ³ãĤº
    -0.07
    ÑģÑı
    -0.07
    ally
    -0.06
    POSITIVE LOGITS
    ity
    0.10
    tı
    0.09
    ties
    0.09
    ti
    0.09
    ysis
    0.08
    gebra
    0.08
    ities
    0.08
    mente
    0.08
    ty
    0.08
    antha
    0.07
    Activations Density 0.012%

    No Known Activations