© 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. 89003
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and related words that emphasize precision and correctness

    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
     Span
    -0.07
     span
    -0.07
    span
    -0.06
     stretch
    -0.06
     scopes
    -0.06
    ogo
    -0.06
     Cad
    -0.06
     Rendering
    -0.06
     Perspective
    -0.06
    arine
    -0.06
    POSITIVE LOGITS
    imals
    0.09
    ades
    0.08
    alion
    0.07
    ignKey
    0.07
    ehler
    0.06
    unci
    0.06
     æī
    0.06
    nga
    0.06
    aju
    0.06
     seals
    0.06
    Activations Density 0.000%

    No Known Activations