© 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. 120654
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to actions or tasks that require completion or integration

    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
     Malone
    -0.07
    odos
    -0.06
     Wish
    -0.06
    »¿
    -0.06
     trp
    -0.06
     Functional
    -0.06
    pollo
    -0.06
    ltk
    -0.06
     Weiner
    -0.05
    ìĨIJ
    -0.05
    POSITIVE LOGITS
     itself
    0.09
    edException
    0.09
     thems
    0.07
    akedown
    0.07
    RAINT
    0.07
    ÏĦαι
    0.07
    à¥Ģय
    0.07
    /stretch
    0.07
     $č↵
    0.07
    AGED
    0.06
    Activations Density 0.099%

    No Known Activations