© 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. 120170
    Prev
    Next
    INDEX
    Explanations

    aspects related to publication formats and newsletter production

    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
    ayers
    -0.07
    .Interop
    -0.06
    ÄĽt
    -0.06
     sö
    -0.06
    drž
    -0.06
    MBER
    -0.06
    thon
    -0.06
    gem
    -0.06
     Vid
    -0.06
    aser
    -0.06
    POSITIVE LOGITS
    frequency
    0.08
     glossy
    0.07
     frequency
    0.07
     Frequency
    0.07
    çݯ
    0.07
     دÙħ
    0.07
    縮
    0.06
     CONTENT
    0.06
    ัà¸ģษ
    0.06
    zon
    0.06
    Activations Density 0.001%

    No Known Activations