© 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. 72272
    Prev
    Next
    INDEX
    Explanations

    references to historical or economic contexts related to systems and policies

    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
    acao
    -0.06
     Oscar
    -0.06
    ugh
    -0.06
     Chun
    -0.06
     DOI
    -0.06
    unya
    -0.06
    illos
    -0.05
     Orn
    -0.05
    ero
    -0.05
     Bird
    -0.05
    POSITIVE LOGITS
    #ad
    0.08
     klu
    0.07
    rac
    0.07
    è
    0.07
    eker
    0.06
    /dc
    0.06
    ebek
    0.06
    presso
    0.06
    .va
    0.06
    .HE
    0.06
    Activations Density 0.045%

    No Known Activations