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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 44443
    Prev
    Next
    INDEX
    Explanations

    characters and symbols from a non-Latin script, indicating content written in a specific language

    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
     Hindered
    -0.08
    اسطة
    -0.07
     Blowjob
    -0.07
    езÑĥлÑĮÑĤ
    -0.06
    çĦ¡ãģĹãģ
    -0.06
     позволÑı
    -0.06
     колиÑĩе
    -0.06
     Milf
    -0.06
     ÑģоÑħÑĢа
    -0.06
     ÑįкÑģплÑĥаÑĤа
    -0.06
    POSITIVE LOGITS
     ÐijоÑĢ
    0.13
     Ðļ
    0.12
     ÐĽ
    0.12
     Ш
    0.12
     Ðĵ
    0.12
     Ðĸ
    0.12
     ÐľÐ¾ÑĢ
    0.12
     Ф
    0.12
     ÐļоÑĢ
    0.12
     Ðĵол
    0.12
    Activations Density 0.268%

    No Known Activations