© 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. 15-LLAMASCOPE-RES-131K
    11. 88255
    Prev
    Next
    INDEX
    Explanations

    terms related to ethical and policy guidelines in academic publishing

    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
    ãĥĩãĤ£ãĤ¢
    -0.07
    łģ
    -0.07
    rocket
    -0.07
    edia
    -0.07
    esch
    -0.06
    adia
    -0.06
     Brun
    -0.06
    avors
    -0.06
     Rockefeller
    -0.06
    æľį
    -0.06
    POSITIVE LOGITS
    Allen
    0.07
    law
    0.06
     ambit
    0.06
    .prompt
    0.06
     Chain
    0.06
    ugin
    0.06
    herits
    0.06
    _IMPLEMENT
    0.06
     Allen
    0.06
     retros
    0.06
    Activations Density 0.001%

    No Known Activations