© 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. 97911
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty about future events

    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
    columnName
    -0.08
    оÑĤÑĥ
    -0.08
    uary
    -0.07
    ouv
    -0.07
    uy
    -0.07
    ified
    -0.07
    aca
    -0.07
    /kernel
    -0.07
    izo
    -0.06
    ìĨį
    -0.06
    POSITIVE LOGITS
    ạnh
    0.07
     whether
    0.07
    LOPT
    0.06
     instrument
    0.06
    ience
    0.06
     Casc
    0.06
    ider
    0.06
    relation
    0.05
     Relation
    0.05
    οÏħν
    0.05
    Activations Density 0.004%

    No Known Activations