© 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. 27982
    Prev
    Next
    INDEX
    Explanations

    terms related to multiple sclerosis (MS) and its causes or effects

    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
    ropa
    -0.08
    adar
    -0.08
     palp
    -0.07
    Pros
    -0.07
     मत
    -0.07
    ucken
    -0.07
     wyn
    -0.06
    |required
    -0.06
    bru
    -0.06
    erno
    -0.06
    POSITIVE LOGITS
    afone
    0.07
    zyst
    0.07
     treatment
    0.07
     treated
    0.07
     treat
    0.06
    .definition
    0.06
     onRequest
    0.06
     caused
    0.06
     treatments
    0.06
    .scalablytyped
    0.06
    Activations Density 0.041%

    No Known Activations