© 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. 86773
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ost" or variations of it, indicating a focus on loss or missed opportunities

    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
    idunt
    -0.07
    itect
    -0.07
    rch
    -0.07
    uckle
    -0.07
    ucci
    -0.07
    rice
    -0.07
    iesta
    -0.07
    ault
    -0.07
    APT
    -0.07
    rule
    -0.06
    POSITIVE LOGITS
    ÄĻp
    0.08
    ensibly
    0.08
    ein
    0.08
    etter
    0.08
    rophic
    0.07
    anza
    0.07
    agma
    0.07
    ech
    0.07
    ogan
    0.07
    hetics
    0.07
    Activations Density 0.012%

    No Known Activations