© 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. 240
    Prev
    Next
    INDEX
    Explanations

    references to the concept of appeal 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
    uw
    -0.07
    ackle
    -0.07
    umble
    -0.06
    å½¹
    -0.06
    jk
    -0.06
    sse
    -0.06
    Ïģκ
    -0.06
    ëŁ¼
    -0.06
     Milky
    -0.06
    cheng
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥģ
    0.07
     authority
    0.07
     senses
    0.06
    à¹ĥà¸Ī
    0.06
     taste
    0.06
     qu
    0.06
    lat
    0.06
    ниÑĨе
    0.06
    å®ĭä½ĵ
    0.06
     аÑĥд
    0.06
    Activations Density 0.009%

    No Known Activations