© 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. 71473
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory issues surrounding media and personal data

    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
    òi
    -0.08
    áu
    -0.08
    èĶµ
    -0.07
    itmap
    -0.07
    étique
    -0.07
    ɵ
    -0.07
    nem
    -0.07
    OND
    -0.07
    ÑĤÑĸв
    -0.06
    ätze
    -0.06
    POSITIVE LOGITS
     specifically
    0.06
     actively
    0.06
    881
    0.06
     explicitly
    0.06
     clearly
    0.06
     intention
    0.06
    922
    0.06
     Jar
    0.06
    911
    0.06
    Ùģع
    0.06
    Activations Density 0.030%

    No Known Activations