© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" with varying emphasis

    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
    ascal
    -0.07
    otta
    -0.07
    idan
    -0.07
    enty
    -0.06
     willing
    -0.06
    istik
    -0.06
    loff
    -0.06
    enton
    -0.06
    ifle
    -0.06
    ios
    -0.06
    POSITIVE LOGITS
    .Spring
    0.07
    ÑĦек
    0.07
     LIC
    0.07
    ãn
    0.06
    UGE
    0.06
    ìĿ´ìĸ´
    0.06
    oggler
    0.06
    ugin
    0.06
     respir
    0.06
     дÑĢÑĥ
    0.06
    Activations Density 0.001%

    No Known Activations