© 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. 129320
    Prev
    Next
    INDEX
    Explanations

    questions and hypotheticals regarding strategies, plans, and their effectiveness

    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
    opleft
    -0.08
    ä¸įæĺ¯
    -0.08
    ordion
    -0.07
    rze
    -0.07
    riad
    -0.07
     souvent
    -0.07
     nejen
    -0.07
    ä¸įä¼ļ
    -0.07
    ĥĿ
    -0.07
    atte
    -0.07
    POSITIVE LOGITS
     naopak
    0.10
     simply
    0.09
     merely
    0.09
     just
    0.09
     else
    0.08
     otherwise
    0.08
     somehow
    0.08
     something
    0.08
     elsewhere
    0.07
    something
    0.07
    Activations Density 0.020%

    No Known Activations