© 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. 62604
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or denial

    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
    conditionally
    -0.07
    oader
    -0.07
    CEE
    -0.06
    alon
    -0.06
    /fwlink
    -0.06
     com
    -0.06
    ãĤªãĥª
    -0.06
    asca
    -0.06
    iol
    -0.06
    ugi
    -0.06
    POSITIVE LOGITS
     explicitly
    0.10
     explicit
    0.09
    explicit
    0.09
     overt
    0.09
    Explicit
    0.08
     Explicit
    0.08
     expressly
    0.08
     outward
    0.08
     formal
    0.07
     Formal
    0.07
    Activations Density 0.029%

    No Known Activations