© 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. 129943
    Prev
    Next
    INDEX
    Explanations

    headings and sections in a document

    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
    acock
    -0.08
    ži
    -0.07
    atron
    -0.07
    ãĥ¡ãĥ©
    -0.07
    orest
    -0.07
    sek
    -0.06
    isper
    -0.06
    MBOL
    -0.06
    Ware
    -0.06
    eward
    -0.06
    POSITIVE LOGITS
    oci
    0.07
    likle
    0.07
    æ¡
    0.07
    uste
    0.06
    æŁ´
    0.06
    uki
    0.06
    egis
    0.06
    ваÑĢ
    0.06
    Ïģιά
    0.06
    ises
    0.06
    Activations Density 0.001%

    No Known Activations