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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5349
    Prev
    Next
    INDEX
    Explanations

    the term associated with a publisher

    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
    >NN
    -0.12
    formace
    -0.12
    >manual
    -0.11
     اختÙĦ
    -0.10
    ¯¼
    -0.10
    AndView
    -0.10
    ÐłÐIJ
    -0.10
    «ĺ
    -0.10
    (æĹ¥
    -0.09
     addCriterion
    -0.09
    POSITIVE LOGITS
    â
    0.11
     â
    0.10
    âĢIJ
    0.10
     â̦
    0.08
    ÃĤ
    0.08
     [â̦]
    0.08
     â̦↵
    0.07
     [â̦
    0.07
     
    0.07
     for
    0.07
    Activations Density 0.000%

    No Known Activations