Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5293
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yet."

    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
    alus
    -0.08
    yar
    -0.07
    licated
    -0.07
    ents
    -0.07
    ìĿ¼ìĹIJ
    -0.07
    recht
    -0.06
    yard
    -0.06
    itored
    -0.06
    ãĤĩ
    -0.06
     Erotik
    -0.06
    POSITIVE LOGITS
     another
    0.18
    another
    0.15
    Another
    0.13
     Another
    0.13
     otra
    0.10
     otro
    0.09
    åı¦
    0.09
    åı¦ä¸Ģ
    0.09
     one
    0.07
    ting
    0.07
    Activations Density 0.004%

    No Known Activations