© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16009
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political actions or controversies

    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
    ringe
    -0.07
    éru
    -0.07
    گز
    -0.06
     McCl
    -0.06
    .cmb
    -0.06
     similarly
    -0.06
    kir
    -0.06
    linger
    -0.06
    xmm
    -0.06
     Obrázky
    -0.06
    POSITIVE LOGITS
     tersebut
    0.07
     αÏħÏĦή
    0.06
    iband
    0.06
    iola
    0.06
    .publish
    0.06
    izzy
    0.06
    yp
    0.06
    obec
    0.06
    ded
    0.06
    usi
    0.06
    Activations Density 0.088%

    No Known Activations