© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 55437
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to simplifying processes or concepts

    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
    ish
    -0.10
     à¹Ĩ
    -0.08
    Ø©
    -0.07
    ÃŃ
    -0.07
    ality
    -0.07
    uming
    -0.07
    abouts
    -0.07
    our
    -0.07
    iw
    -0.07
    old
    -0.07
    POSITIVE LOGITS
    cation
    0.09
    ÑģÑĮ
    0.07
    ebo
    0.07
    aton
    0.07
    Ùĩ
    0.06
    ÑĪиÑģÑĮ
    0.06
    PropertyName
    0.06
    ä½ľçĶ¨
    0.06
     Loose
    0.06
    uentes
    0.06
    Activations Density 0.026%

    No Known Activations