© 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. 62592
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate magnitude or extent

    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
    owler
    -0.08
    太éĥİ
    -0.07
     Ends
    -0.06
    öyle
    -0.06
     olm
    -0.06
    егоÑĢ
    -0.06
    омеÑĤ
    -0.06
    ама
    -0.06
    aar
    -0.06
    ãĤ¸ãĤ¢
    -0.06
    POSITIVE LOGITS
     possibilities
    0.09
     ones
    0.08
     examples
    0.07
     thereof
    0.07
    ayne
    0.07
     specifics
    0.06
    iglia
    0.06
     possibility
    0.06
     such
    0.06
    Others
    0.06
    Activations Density 0.043%

    No Known Activations