© 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 EvalsExportsAPI 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. 61023
    Prev
    Next
    INDEX
    Explanations

    instructions and guidelines regarding medication usage

    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
    utow
    -0.06
    ivent
    -0.06
     toll
    -0.06
    mini
    -0.06
     Gallagher
    -0.05
    otton
    -0.05
    oot
    -0.05
     ActiveSupport
    -0.05
     Barr
    -0.05
    awy
    -0.05
    POSITIVE LOGITS
    amik
    0.08
    orges
    0.07
    anik
    0.07
    éĿ
    0.07
    ãĥ³ãĥĶ
    0.07
    ç¾
    0.07
     Cush
    0.07
     Alv
    0.07
    å¾½
    0.06
    .useState
    0.06
    Activations Density 0.007%

    No Known Activations