© 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. 2150
    Prev
    Next
    INDEX
    Explanations

    words that express judgment and evaluations regarding actions or situations

    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
    .tm
    -0.06
    nbsp
    -0.06
    è¼Ķ
    -0.06
    odb
    -0.06
    undle
    -0.06
    indi
    -0.06
    elda
    -0.06
    esp
    -0.06
    aleb
    -0.05
    undler
    -0.05
    POSITIVE LOGITS
    #aa
    0.07
    SystemService
    0.07
    #af
    0.06
    PFN
    0.06
    ICC
    0.06
    ButtonDown
    0.06
    levation
    0.06
    dea
    0.06
    pras
    0.06
    tee
    0.06
    Activations Density 0.033%

    No Known Activations