© 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. 15-LLAMASCOPE-RES-131K
    11. 754
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluation and grading 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
     ún
    -0.09
    ï¼ł
    -0.09
    ephir
    -0.09
     arac
    -0.09
    Ģ
    -0.09
    uml
    -0.09
    .Serial
    -0.09
    ÎIJ
    -0.09
    voje
    -0.08
     prostitut
    -0.08
    POSITIVE LOGITS
     _____
    0.06
    0.05
    ®
    0.05
     Doming
    0.05
     d
    0.05
     https
    0.05
     ____
    0.05
    âĢ¦↵
    0.05
    tos
    0.05
    æĽľ
    0.05
    Activations Density 0.007%

    No Known Activations