© 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 EvalsExportsAPI 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. 125594
    Prev
    Next
    INDEX
    Explanations

    phrases related to the capabilities and features of a game or application

    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
     mo
    -0.06
    ,
    -0.06
     sm
    -0.06
     vit
    -0.06
    ãĤ±ãĥ¼ãĤ¹
    -0.06
    Portfolio
    -0.06
    äºĨ解
    -0.05
    ante
    -0.05
     respectively
    -0.05
     f
    -0.05
    POSITIVE LOGITS
    AtPath
    0.08
    íĮIJ
    0.08
    .googlecode
    0.08
    ç´Ļ
    0.08
    /demo
    0.07
    _FUN
    0.07
    ãĥŃãĥ³
    0.07
    pta
    0.07
    fun
    0.07
    anje
    0.07
    Activations Density 0.007%

    No Known Activations