© 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. 96075
    Prev
    Next
    INDEX
    Explanations

    punctuation and terms related to storytelling or narration

    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
     Mil
    -0.06
    udes
    -0.06
    zo
    -0.06
    ught
    -0.06
    оÑĢони
    -0.06
    sic
    -0.06
    ughs
    -0.06
     kostenlose
    -0.06
    zos
    -0.06
    istrar
    -0.06
    POSITIVE LOGITS
    -wide
    0.07
    fat
    0.06
    TURE
    0.06
    iphery
    0.06
    737
    0.06
    WithData
    0.06
    BUG
    0.06
    IALOG
    0.06
    .cells
    0.06
    <dim
    0.06
    Activations Density 0.052%

    No Known Activations