© 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. 17-LLAMASCOPE-RES-131K
    11. 124171
    Prev
    Next
    INDEX
    Explanations

    references to biological structures and processes, particularly involving proteins and glycoproteins

    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
    abus
    -0.08
    ash
    -0.07
    pillar
    -0.07
    phylum
    -0.07
    fak
    -0.06
    mpp
    -0.06
     mitochond
    -0.06
     ash
    -0.06
     mitochondrial
    -0.06
    Dies
    -0.06
    POSITIVE LOGITS
     ÑģекÑĢеÑĤ
    0.08
    RIA
    0.07
    resher
    0.07
    ợi
    0.07
     secret
    0.07
    Album
    0.07
    ycastle
    0.07
    ubah
    0.07
    ibble
    0.07
    obao
    0.07
    Activations Density 0.022%

    No Known Activations