© 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. 15-LLAMASCOPE-RES-131K
    11. 103544
    Prev
    Next
    INDEX
    Explanations

    sections marked with region or endregion comments typically used in programming documentation

    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
    podob
    -0.08
    å¥ij
    -0.08
    eczy
    -0.07
    udeau
    -0.07
    bers
    -0.07
    ÑĢÑĸд
    -0.06
    apyrus
    -0.06
    ãģİ
    -0.06
     cass
    -0.06
     nues
    -0.06
    POSITIVE LOGITS
     Bloody
    0.06
    ORA
    0.06
    Į
    0.06
    -fontawesome
    0.06
    inder
    0.06
    agal
    0.06
    uluk
    0.05
    909
    0.05
    -AA
    0.05
    Blo
    0.05
    Activations Density 0.031%

    No Known Activations