© 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. 79945
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and academic training

    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
    idot
    -0.07
    isor
    -0.07
    agnost
    -0.07
     cane
    -0.06
    icode
    -0.06
    odiac
    -0.06
    ikit
    -0.06
    amel
    -0.06
    (Void
    -0.06
     fore
    -0.06
    POSITIVE LOGITS
     ethical
    0.07
     reviewer
    0.07
     ethics
    0.07
    伦
    0.07
    ethical
    0.07
     reviewers
    0.07
     Colony
    0.06
     Ethics
    0.06
     Eth
    0.06
    _eth
    0.06
    Activations Density 0.001%

    No Known Activations