© 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. 18822
    Prev
    Next
    INDEX
    Explanations

    indicators of listing or documentation

    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
    ardash
    -0.07
    bery
    -0.07
    empt
    -0.06
    acement
    -0.06
    levator
    -0.06
    DevExpress
    -0.06
    efe
    -0.06
    juven
    -0.06
    undi
    -0.06
     æĿ
    -0.06
    POSITIVE LOGITS
     Alumni
    0.07
    uin
    0.06
    aler
    0.06
    ÐļТ
    0.06
    yro
    0.06
     alphabetical
    0.06
    aug
    0.06
    ĥ
    0.06
    gorith
    0.05
     VÄĽ
    0.05
    Activations Density 0.000%

    No Known Activations