© 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. 74245
    Prev
    Next
    INDEX
    Explanations

    programming-related file handling and data processing 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
    -lang
    -0.07
    EH
    -0.07
    stro
    -0.07
    .Lang
    -0.07
    keh
    -0.06
    acia
    -0.06
     Rudy
    -0.06
     insets
    -0.06
     Lang
    -0.06
    raction
    -0.06
    POSITIVE LOGITS
    INAL
    0.07
    inal
    0.07
    ichel
    0.06
    eling
    0.06
     Cum
    0.06
    _compat
    0.06
     Kath
    0.06
    .gf
    0.06
    é¡ĺãģĦ
    0.06
    assin
    0.06
    Activations Density 0.000%

    No Known Activations