© 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. 88754
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of organizational expectations and commitments

    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
     get
    -0.06
    à¹īวย
    -0.06
    actly
    -0.06
    Vý
    -0.06
    çĴ
    -0.06
    aign
    -0.05
     die
    -0.05
    reso
    -0.05
    acÃŃ
    -0.05
     rab
    -0.05
    POSITIVE LOGITS
    okud
    0.07
     ayrıca
    0.07
    @qq
    0.07
    ÙĤات
    0.07
    ÏħÏĢ
    0.07
    ök
    0.07
    \Migration
    0.07
    irma
    0.07
    SED
    0.07
    okrat
    0.07
    Activations Density 0.031%

    No Known Activations