© 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. 3330
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "at" in various contexts

    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
    ylum
    -0.07
    ioc
    -0.06
    olas
    -0.06
    statt
    -0.06
    hd
    -0.06
    lash
    -0.06
    à¥įसर
    -0.06
    iot
    -0.06
    ih
    -0.06
    _scan
    -0.06
    POSITIVE LOGITS
    зÑĮ
    0.08
    ̣
    0.06
     ("-
    0.06
    akit
    0.06
    RECT
    0.06
    tabla
    0.06
     table
    0.06
    éIJĺ
    0.06
     fallen
    0.06
    енÑĮ
    0.06
    Activations Density 0.033%

    No Known Activations