© 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. 60991
    Prev
    Next
    INDEX
    Explanations

    keywords related to online account management and service features

    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
    ebek
    -0.10
    tesy
    -0.10
    HITE
    -0.09
     eskort
    -0.09
     ëĦ¤ìĿ´íĬ¸
    -0.09
    /cop
    -0.09
     addCriterion
    -0.09
    estre
    -0.09
    ÅŁk
    -0.09
    anny
    -0.08
    POSITIVE LOGITS
     option
    0.08
     .
    0.07
     pul
    0.06
     ,
    0.06
     (
    0.06
     .↵
    0.06
     Mori
    0.06
    u
    0.06
    (s
    0.05
     or
    0.05
    Activations Density 0.009%

    No Known Activations