© 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. 80699
    Prev
    Next
    INDEX
    Explanations

    terms related to replacing or modifying elements in various contexts

    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
    uali
    -0.08
    raquo
    -0.08
    retty
    -0.07
    umbledore
    -0.07
    ariat
    -0.07
    ypsum
    -0.07
    κοÏħ
    -0.07
    lico
    -0.07
    uela
    -0.07
    untu
    -0.07
    POSITIVE LOGITS
     bills
    0.05
     Sons
    0.05
     Hung
    0.05
    ands
    0.05
     Hansen
    0.05
    rous
    0.05
    phant
    0.05
    le
    0.05
    angled
    0.05
    And
    0.05
    Activations Density 0.000%

    No Known Activations