© 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. 92120
    Prev
    Next
    INDEX
    Explanations

    elements related to evaluation and comparison in contexts like employment or contract terms

    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
    ãĥĥãĥĹ
    -0.07
    bk
    -0.07
    âĢ¦↵↵↵
    -0.07
    ForResource
    -0.06
    lah
    -0.06
    ÃŁerdem
    -0.06
    ldr
    -0.06
    AWN
    -0.06
    ARGS
    -0.06
    dir
    -0.06
    POSITIVE LOGITS
    oubles
    0.06
     ÑĦевÑĢа
    0.06
    /not
    0.06
     Yani
    0.06
    anness
    0.06
    ensus
    0.06
    agens
    0.06
    £
    0.06
    æ¸Ī
    0.06
    #aa
    0.06
    Activations Density 0.047%

    No Known Activations