© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5948
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate time durations and countdowns

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    heiro
    -0.07
    cade
    -0.06
     wave
    -0.06
    sville
    -0.06
    VILLE
    -0.06
     rank
    -0.06
    öy
    -0.06
    -0.06
    ado
    -0.05
    alement
    -0.05
    POSITIVE LOGITS
    andal
    0.09
    STITUTE
    0.08
    styleType
    0.08
    aylight
    0.08
    agged
    0.07
    SBATCH
    0.07
     Ago
    0.07
    agues
    0.07
    £½
    0.07
    ],&
    0.07
    Activations Density 0.017%

    No Known Activations