© 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. 73902
    Prev
    Next
    INDEX
    Explanations

    phrases that express high recommendations or positive endorsements of books

    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
    angu
    -0.07
     pip
    -0.06
     Eaton
    -0.06
    izard
    -0.06
     Unused
    -0.06
     Vác
    -0.06
    ENDER
    -0.06
     unused
    -0.06
    iska
    -0.06
    ittest
    -0.06
    POSITIVE LOGITS
    cete
    0.09
     recommended
    0.09
     recommendation
    0.09
     recommend
    0.08
     Recommend
    0.08
    recommended
    0.08
    Recommended
    0.08
    anse
    0.07
    outil
    0.07
     LENG
    0.07
    Activations Density 0.022%

    No Known Activations