© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83494
    Prev
    Next
    INDEX
    Explanations

    references to children and their interactions or experiences

    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
    gens
    -0.06
    itesse
    -0.06
    aes
    -0.05
    æīĭãĤĴ
    -0.05
    esco
    -0.05
     BSD
    -0.05
    BSD
    -0.05
    oslav
    -0.05
    emm
    -0.05
    лоÑģÑĮ
    -0.05
    POSITIVE LOGITS
     Äijang
    0.15
    æŃ£åľ¨
    0.12
    à¸ģำล
    0.11
     estamos
    0.09
     are
    0.09
     estão
    0.08
    æĺ¯åľ¨
    0.08
     estar
    0.08
    ãģĹãģ¦ãģĦãĤĭ
    0.08
    ãģĹãģ¦ãģĦãģ¾ãģĻ
    0.08
    Activations Density 0.044%

    No Known Activations