© 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. 75333
    Prev
    Next
    INDEX
    Explanations

    references to governance and regulation

    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
    _stdio
    -0.06
     D
    -0.06
     W
    -0.06
    ngo
    -0.06
     xa
    -0.06
     einem
    -0.06
     denen
    -0.06
    aign
    -0.05
    hall
    -0.05
     somebody
    -0.05
    POSITIVE LOGITS
    该
    0.11
    該
    0.10
    è¿Ļ个
    0.09
     this
    0.09
    'gc
    0.08
    atel
    0.08
    edl
    0.08
    ì§Ģëħ¸
    0.08
    ë¨
    0.08
     ÑįÑĤоÑĤ
    0.08
    Activations Density 0.149%

    No Known Activations