© 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. 98267
    Prev
    Next
    INDEX
    Explanations

    words that indicate uncertainty or ambiguity in descriptions

    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
    YRO
    -0.08
    ancel
    -0.08
    /proto
    -0.07
    GLOBALS
    -0.07
    acco
    -0.07
    drs
    -0.07
     sdl
    -0.06
    ÏĦε
    -0.06
    unker
    -0.06
    ær
    -0.06
    POSITIVE LOGITS
     Ung
    0.07
    ungan
    0.06
    293
    0.06
    cak
    0.06
    edith
    0.06
     Either
    0.06
     thirds
    0.06
     záp
    0.05
     Derrick
    0.05
    Lang
    0.05
    Activations Density 0.030%

    No Known Activations