© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2896
    Prev
    Next
    INDEX
    Explanations

    instances of time-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
    endra
    -0.08
    _TestCase
    -0.07
    ivos
    -0.07
    illez
    -0.07
    igma
    -0.07
    avou
    -0.07
    ertino
    -0.07
    roti
    -0.07
    byn
    -0.06
    à¸Ļà¸Ń
    -0.06
    POSITIVE LOGITS
     opport
    0.09
    528
    0.07
     appropriate
    0.06
    ewed
    0.06
    ekt
    0.06
    ague
    0.06
    GIT
    0.06
    397
    0.06
     intervals
    0.05
    па
    0.05
    Activations Density 0.030%

    No Known Activations