© 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. 88803
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to user actions and interactions

    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
     Innoc
    -0.07
    ?url
    -0.07
    (ib
    -0.06
    agen
    -0.06
    358
    -0.06
    (delegate
    -0.06
    any
    -0.06
    еÑģÑĤÑĮ
    -0.06
    ØŃÙĬ
    -0.06
    æı
    -0.06
    POSITIVE LOGITS
    nish
    0.06
    emailer
    0.06
    ebb
    0.06
    gow
    0.06
    odo
    0.06
    URN
    0.06
    TRACE
    0.06
    roperty
    0.06
    tesy
    0.06
    iesel
    0.06
    Activations Density 0.006%

    No Known Activations