© 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. 80032
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "time" and its related phrases

    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
     ÙħÙĦت
    -0.07
     thus
    -0.06
    lıģının
    -0.06
    bury
    -0.06
     continues
    -0.06
    thus
    -0.06
    Äįet
    -0.06
    aly
    -0.06
    ivot
    -0.06
    inue
    -0.06
    POSITIVE LOGITS
    instead
    0.08
     instead
    0.08
    ãĥ¼ãĤ¯
    0.07
    знаÑĩа
    0.07
    isors
    0.07
    ãģ§ãģ¯ãģªãģı
    0.07
    Rather
    0.07
    asio
    0.07
    ÑĤÑĢо
    0.07
    rather
    0.07
    Activations Density 0.010%

    No Known Activations