© 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. 81719
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular apoptosis and mitochondrial 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
    ephir
    -0.07
    AGMA
    -0.07
    phem
    -0.07
     Shooter
    -0.07
    amerate
    -0.07
    ãĤĮãģ©
    -0.07
    opak
    -0.06
    egment
    -0.06
    edio
    -0.06
    _mtime
    -0.06
    POSITIVE LOGITS
     death
    0.10
     apopt
    0.09
    -death
    0.09
     apoptosis
    0.09
     cas
    0.09
    death
    0.08
     Death
    0.08
     execution
    0.08
     Execution
    0.08
     suicide
    0.08
    Activations Density 0.022%

    No Known Activations