© 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. 5-LLAMASCOPE-RES-131K
    11. 125860
    Prev
    Next
    INDEX
    Explanations

    instances of the word "overwhelming" and its variations

    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
    iset
    -0.08
    Ñĵ
    -0.07
    uffy
    -0.07
    atsu
    -0.07
    ernel
    -0.07
    icable
    -0.07
     Malone
    -0.07
    asz
    -0.06
    igi
    -0.06
    zan
    -0.06
    POSITIVE LOGITS
    ingly
    0.11
     majority
    0.07
     ÐŁÑĢа
    0.06
    347
    0.06
    lest
    0.06
    HCI
    0.06
    amet
    0.06
     amounts
    0.06
    ly
    0.06
     Cer
    0.06
    Activations Density 0.005%

    No Known Activations