© 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. 26879
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and methodologies

    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
     Sty
    -0.06
    storybook
    -0.06
     Nam
    -0.06
    rale
    -0.06
    sects
    -0.05
    uby
    -0.05
    strncmp
    -0.05
    ç«ĭãģ¡
    -0.05
    uede
    -0.05
    Nam
    -0.05
    POSITIVE LOGITS
    åľŁ
    0.07
     colon
    0.07
     AssemblyVersion
    0.06
    κοÏį
    0.06
    eturn
    0.06
    AUSE
    0.06
    onaut
    0.06
    176
    0.06
    ocked
    0.06
    ť
    0.06
    Activations Density 0.003%

    No Known Activations