© 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. 31601
    Prev
    Next
    INDEX
    Explanations

    details related to event schedules and gatherings

    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
    VP
    -0.07
    zsche
    -0.07
     Invitation
    -0.06
    anche
    -0.06
    peek
    -0.06
    ushima
    -0.06
    DEL
    -0.06
    anium
    -0.06
    laus
    -0.06
     Glas
    -0.06
    POSITIVE LOGITS
     ready
    0.08
    .ready
    0.08
    ready
    0.08
     starting
    0.07
    arsi
    0.07
     Ready
    0.07
    rier
    0.07
     departure
    0.07
     rallying
    0.07
     conven
    0.07
    Activations Density 0.021%

    No Known Activations