© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    connections between diseases, deficiencies, and their underlying mechanisms

    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
    ODO
    -0.06
    åĪ¶åº¦
    -0.06
     induce
    -0.06
    ामà¤Ĺ
    -0.06
     predominant
    -0.06
    _legend
    -0.06
    chl
    -0.06
     Knight
    -0.06
     ÃŃ
    -0.06
    vestment
    -0.06
    POSITIVE LOGITS
     mechanisms
    0.08
     mechanism
    0.07
    (*)(
    0.07
     path
    0.07
     Mechan
    0.07
     cascade
    0.07
     nid
    0.07
    ingo
    0.07
    opard
    0.07
    ascade
    0.06
    Activations Density 0.023%

    No Known Activations