© 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. 59757
    Prev
    Next
    INDEX
    Explanations

    temporal comparisons and durations

    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
    .onCreate
    -0.07
    esk
    -0.07
    otos
    -0.06
    _INCLUDED
    -0.06
    enticate
    -0.06
    asje
    -0.06
    alte
    -0.06
    bild
    -0.06
    isd
    -0.06
    efon
    -0.06
    POSITIVE LOGITS
    favor
    0.06
    omba
    0.06
     throughout
    0.06
     favor
    0.06
    çĶ²
    0.06
     across
    0.06
    jal
    0.06
    Kal
    0.06
    _TestCase
    0.06
    usercontent
    0.06
    Activations Density 0.041%

    No Known Activations