© 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. 129198
    Prev
    Next
    INDEX
    Explanations

    specific details related to measurements and instructions 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
    éĹ
    -0.06
     but
    -0.06
     would
    -0.06
    ↵
    -0.06
     Barton
    -0.05
     Certain
    -0.05
    ohn
    -0.05
     But
    -0.05
     ten
    -0.05
    uyu
    -0.05
    POSITIVE LOGITS
     nhé
    0.10
    åIJ¦
    0.10
     tránh
    0.09
    наÑĩе
    0.09
    ç¡®
    0.09
    ä¸įè¦ģ
    0.09
     mutlaka
    0.08
    pper
    0.08
    æīįèĥ½
    0.08
     otherwise
    0.08
    Activations Density 0.037%

    No Known Activations