© 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. 75790
    Prev
    Next
    INDEX
    Explanations

    concepts related to educational frameworks and community engagement strategies

    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
    urette
    -0.06
    aku
    -0.06
    ubar
    -0.06
    quo
    -0.06
     Obt
    -0.06
    aight
    -0.06
    eton
    -0.06
    emade
    -0.06
    ayload
    -0.05
    azu
    -0.05
    POSITIVE LOGITS
     approach
    0.08
     approaches
    0.07
    коÑĤ
    0.07
     подÑħод
    0.07
     Integrated
    0.07
    762
    0.06
    paged
    0.06
    ocker
    0.06
     overdue
    0.06
     advanced
    0.06
    Activations Density 0.041%

    No Known Activations