© 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. 9-LLAMASCOPE-RES-131K
    11. 98846
    Prev
    Next
    INDEX
    Explanations

    questions about various topics, particularly those involving decision-making or uncertainty

    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
    ertino
    -0.08
    entifier
    -0.08
    arent
    -0.07
    \Blueprint
    -0.07
    ı
    -0.07
    aye
    -0.07
    iya
    -0.07
    sville
    -0.07
    eo
    -0.07
    ÅĪ
    -0.07
    POSITIVE LOGITS
     whether
    0.08
     Whether
    0.07
    whether
    0.07
     Mot
    0.06
    Whether
    0.06
    ãĥ³ãĥĢ
    0.06
     Campbell
    0.06
    íĥĦ
    0.06
     Uploaded
    0.06
    apor
    0.06
    Activations Density 0.013%

    No Known Activations