© 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 EvalsExportsAPI 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. 88498
    Prev
    Next
    INDEX
    Explanations

    instances of the word "enough."

    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
    asons
    -0.07
    herits
    -0.06
    Highlighted
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    vez
    -0.06
    TRL
    -0.06
    etur
    -0.06
    ContentView
    -0.06
    far
    -0.06
    -house
    -0.06
    POSITIVE LOGITS
    alore
    0.07
    åı£
    0.07
    OfFile
    0.07
    unte
    0.06
     enough
    0.06
    838
    0.06
     bahwa
    0.06
     that
    0.06
    .series
    0.06
    UC
    0.06
    Activations Density 0.014%

    No Known Activations