© 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. 95213
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or identity in various contexts

    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
    ipt
    -0.06
     ÙħØ´
    -0.06
     Ih
    -0.06
    -banner
    -0.06
     UD
    -0.05
    bz
    -0.05
     ----------------------------------------------------------------------------↵
    -0.05
    vil
    -0.05
    rex
    -0.05
     Lifestyle
    -0.05
    POSITIVE LOGITS
    ÂŃi
    0.07
    æĤŁ
    0.07
    ubbo
    0.07
     Stretch
    0.07
    aml
    0.07
    cona
    0.07
    achte
    0.07
    uras
    0.07
     Peek
    0.07
    ony
    0.07
    Activations Density 0.043%

    No Known Activations