© 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. 106180
    Prev
    Next
    INDEX
    Explanations

    names or references associated with legal contexts and entities

    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
    .bunifuFlatButton
    -0.10
    Ñĥг
    -0.10
     акÑĤи
    -0.09
    ë¨
    -0.09
    еÑĢÑĪ
    -0.09
    ÑĢади
    -0.09
    .Reporting
    -0.09
    ëį°ìĿ´íĬ¸
    -0.08
    cona
    -0.08
    ãĤĵãģ©
    -0.08
    POSITIVE LOGITS
    ...↵
    0.07
    âĢ¦↵
    0.07
    ..
    0.06
     Cres
    0.06
    ..↵
    0.06
    ...
    0.05
    tab
    0.05
     The
    0.05
    ..."↵
    0.05
     [âĢ¦]↵
    0.05
    Activations Density 0.018%

    No Known Activations