© 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. 27014
    Prev
    Next
    INDEX
    Explanations

    phrases related to downloading and sharing digital content

    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
     Pipes
    -0.06
     Lig
    -0.06
     Mare
    -0.06
     Lage
    -0.06
     lig
    -0.06
     tw
    -0.06
     Pig
    -0.06
     Siz
    -0.05
     Sloan
    -0.05
    ubat
    -0.05
    POSITIVE LOGITS
    tuk
    0.07
    reich
    0.07
    TOTYPE
    0.07
    _related
    0.07
    insic
    0.07
    buster
    0.07
    ailles
    0.06
    .Script
    0.06
    ieber
    0.06
    AXB
    0.06
    Activations Density 0.010%

    No Known Activations