© 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. 15-LLAMASCOPE-RES-131K
    11. 86632
    Prev
    Next
    INDEX
    Explanations

    phrases related to medication usage and guidelines

    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
     precedence
    -0.06
    adata
    -0.06
     classical
    -0.06
    oker
    -0.06
     Classical
    -0.06
    oref
    -0.06
     Era
    -0.06
     lite
    -0.06
     Classic
    -0.05
    nave
    -0.05
    POSITIVE LOGITS
     baÅŁÄ±na
    0.08
    clid
    0.07
    elig
    0.07
    ramer
    0.07
    esktop
    0.07
     Seks
    0.06
     Elig
    0.06
    ensch
    0.06
    orny
    0.06
     voksne
    0.06
    Activations Density 0.022%

    No Known Activations