© 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. 84331
    Prev
    Next
    INDEX
    Explanations

    terms related to business advisories and legal considerations

    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
    asto
    -0.07
     Sabb
    -0.06
    _RS
    -0.06
     hvordan
    -0.06
     helf
    -0.06
     pkg
    -0.06
    loe
    -0.06
     neob
    -0.06
    992
    -0.06
    aż
    -0.06
    POSITIVE LOGITS
    Äĵ
    0.07
    Uvs
    0.06
    estate
    0.06
     plan
    0.06
    ÑıÑĩ
    0.06
    æŁ±
    0.06
     поба
    0.06
    è¸ı
    0.06
    éĥ½ä¼ļ
    0.06
     batches
    0.06
    Activations Density 0.001%

    No Known Activations