© 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. 93244
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and substance use disorders

    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
    foy
    -0.08
     Pix
    -0.07
    emie
    -0.07
    ÎIJ
    -0.07
    EdgeInsets
    -0.07
    ëĿ¼ëıĦ
    -0.06
     typename
    -0.06
    ç¦ıåĪ©
    -0.06
    acerb
    -0.06
     ciz
    -0.06
    POSITIVE LOGITS
     treatment
    0.08
     Treatment
    0.07
     treating
    0.06
     treatments
    0.06
     expanded
    0.06
     expanding
    0.06
    places
    0.06
     nal
    0.06
    uct
    0.05
     Treat
    0.05
    Activations Density 0.001%

    No Known Activations