© 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. 89011
    Prev
    Next
    INDEX
    Explanations

    expressions related to public finance and education choices

    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
    icode
    -0.08
    imestone
    -0.07
    ANNOT
    -0.07
    ayah
    -0.07
     Americas
    -0.07
    udas
    -0.07
    eyin
    -0.07
    appa
    -0.06
    orelease
    -0.06
    ikhail
    -0.06
    POSITIVE LOGITS
     again
    0.08
     also
    0.08
     equally
    0.07
     same
    0.07
    iggs
    0.07
     Again
    0.06
    ãģĿãĤĮãģ¯
    0.06
    122
    0.06
     firstly
    0.06
    phe
    0.06
    Activations Density 0.034%

    No Known Activations