© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    references to different times of the day

    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
    иÑģÑĮ
    -0.07
    ÑĢап
    -0.07
    unsch
    -0.06
     Sle
    -0.06
    verbatim
    -0.06
    UTO
    -0.06
    zew
    -0.06
    anders
    -0.06
    ë°Ģ
    -0.06
     Weekly
    -0.06
    POSITIVE LOGITS
    MEA
    0.07
    stem
    0.06
    erk
    0.06
     Wah
    0.06
    asty
    0.06
    occo
    0.06
    irst
    0.06
    CCI
    0.06
    eldorf
    0.06
    631
    0.06
    Activations Density 0.016%

    No Known Activations