© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28009
    Prev
    Next
    INDEX
    Explanations

    scientific terms and descriptions related to molecular analysis and biological studies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Vernon
    -0.07
    lew
    -0.07
    ½
    -0.06
     Norman
    -0.06
    decorate
    -0.06
    oksen
    -0.06
    gil
    -0.06
    itational
    -0.06
    ease
    -0.06
    roduced
    -0.06
    POSITIVE LOGITS
    annis
    0.09
     study
    0.09
    roperties
    0.08
     characteristics
    0.08
     investigation
    0.08
     profile
    0.08
     properties
    0.08
     Characteristics
    0.07
    profile
    0.07
     aspects
    0.07
    Activations Density 0.044%

    No Known Activations