© 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. 81668
    Prev
    Next
    INDEX
    Explanations

    elements related to software or programming dependencies

    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
    hone
    -0.09
    Ñıд
    -0.08
    estro
    -0.08
    ãĥĥãĥĹ
    -0.07
    ixo
    -0.07
    ãĥ¼ãĥ©
    -0.07
     Linh
    -0.07
    .getInfo
    -0.07
    amac
    -0.07
    заб
    -0.07
    POSITIVE LOGITS
     together
    0.06
    ackers
    0.06
     framework
    0.06
    ,
    0.06
     ad
    0.06
     dependent
    0.05
    261
    0.05
     Sud
    0.05
     plus
    0.05
     cra
    0.05
    Activations Density 0.004%

    No Known Activations