© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56947
    Prev
    Next
    INDEX
    Explanations

    sections labeled as "Introduction"

    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
    WithDuration
    -0.06
     Fly
    -0.06
    dos
    -0.06
    浦
    -0.06
    elib
    -0.06
    herits
    -0.06
    ilter
    -0.06
    rana
    -0.06
     DBNull
    -0.06
    orate
    -0.06
    POSITIVE LOGITS
    UIS
    0.08
    uis
    0.07
    »
    0.06
    ÏĦαν
    0.06
     stol
    0.06
    нÑĸÑģÑĤ
    0.06
    TypeName
    0.06
     Hooks
    0.06
     Admir
    0.06
    ONA
    0.06
    Activations Density 0.000%

    No Known Activations