© 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. 59449
    Prev
    Next
    INDEX
    Explanations

    names of companies and organizations

    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
    jab
    -0.07
    бо
    -0.07
    lish
    -0.07
    chers
    -0.07
    lew
    -0.07
    asma
    -0.07
    ouro
    -0.07
     зави
    -0.07
    urg
    -0.07
    sen
    -0.07
    POSITIVE LOGITS
    973
    0.06
    ael
    0.06
     leadership
    0.06
    954
    0.06
     yourselves
    0.06
    956
    0.06
    347
    0.06
    让æĪij
    0.06
    567
    0.06
     vect
    0.05
    Activations Density 0.010%

    No Known Activations