© 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. 89828
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mock" 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
    akin
    -0.08
    ủi
    -0.07
    ầu
    -0.07
    ccione
    -0.07
    arası
    -0.07
    .Inf
    -0.07
    ç«¥
    -0.07
    -thirds
    -0.07
    oggle
    -0.07
    inals
    -0.07
    POSITIVE LOGITS
    ingly
    0.13
    tober
    0.11
    ington
    0.08
    à¹Ģà¸ģà¸Ńร
    0.08
    intosh
    0.08
    nowledge
    0.07
    tail
    0.07
    sters
    0.07
    eds
    0.07
    eries
    0.07
    Activations Density 0.003%

    No Known Activations