© 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. 17589
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating quantity or degree

    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
     firstly
    -0.08
     totiž
    -0.07
     however
    -0.07
    ilst
    -0.07
     zwar
    -0.06
    ered
    -0.06
     Firstly
    -0.06
    ý
    -0.06
    rence
    -0.06
    ensely
    -0.06
    POSITIVE LOGITS
     therein
    0.09
     consequently
    0.08
     accordingly
    0.08
     ìĿ´ë¥¼
    0.08
     thereof
    0.08
     ê·¸ê²ĥ
    0.07
     deren
    0.07
    åĽłæѤ
    0.07
    ãĥ¼ãĥ³
    0.07
    reso
    0.07
    Activations Density 0.001%

    No Known Activations