© 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. 69200
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth or development

    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
     bulk
    -0.07
    IRT
    -0.07
    atte
    -0.06
    coni
    -0.06
    ichel
    -0.06
     ãĥ©
    -0.06
    uang
    -0.06
    wd
    -0.06
     #
    -0.06
     growing
    -0.06
    POSITIVE LOGITS
    RuleContext
    0.07
    uda
    0.07
    omain
    0.07
    adors
    0.07
    nda
    0.06
    æĢĿ
    0.06
    ColumnType
    0.06
    lied
    0.06
    AGMA
    0.06
     lesbi
    0.06
    Activations Density 0.000%

    No Known Activations