© 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. 119163
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or academic discourse, particularly in the fields of sociology and biology

    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
    erce
    -0.07
    leich
    -0.07
    endar
    -0.07
     MainAxisAlignment
    -0.06
     Grade
    -0.06
    URLException
    -0.06
    -spin
    -0.06
     UICollectionViewCell
    -0.06
    uze
    -0.06
     itself
    -0.06
    POSITIVE LOGITS
    üstü
    0.07
    åĪ¥
    0.07
    ķìĿ¸
    0.07
    types
    0.07
    ë³Ħ
    0.07
     types
    0.07
    odb
    0.07
    lots
    0.07
    MetaData
    0.07
    ypes
    0.06
    Activations Density 0.066%

    No Known Activations