© 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. 30268
    Prev
    Next
    INDEX
    Explanations

    references to physiological processes and conditions relating to the hypothalamus

    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
     Mobility
    -0.08
     mobility
    -0.08
    uckle
    -0.07
    vit
    -0.07
    umpt
    -0.07
    quete
    -0.07
    ndx
    -0.07
    ignet
    -0.07
    enchmark
    -0.06
    udiant
    -0.06
    POSITIVE LOGITS
     hypoth
    0.09
     vag
    0.08
    ä¸ĺ
    0.07
     regulation
    0.07
     ASIC
    0.06
     feedback
    0.06
    exc
    0.06
     exc
    0.06
    CommandLine
    0.06
     links
    0.06
    Activations Density 0.009%

    No Known Activations