© 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. 28222
    Prev
    Next
    INDEX
    Explanations

    references to government officials and their statements or actions

    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
     Kn
    -0.06
    265
    -0.06
    )(__
    -0.06
     SL
    -0.05
     sl
    -0.05
     Goldman
    -0.05
    639
    -0.05
     consent
    -0.05
     source
    -0.05
     et
    -0.05
    POSITIVE LOGITS
    indre
    0.09
    ertas
    0.08
    reich
    0.07
    urent
    0.07
    icode
    0.07
    rve
    0.07
     speaking
    0.07
    ebek
    0.07
    ksam
    0.07
     remarks
    0.07
    Activations Density 0.044%

    No Known Activations