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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108206
    Prev
    Next
    INDEX
    Explanations

    repetitive conjunctions and phrases indicating connection or inclusion

    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
    -fluid
    -0.07
     Guys
    -0.06
    guard
    -0.06
    ä¸Ģ次
    -0.06
    evin
    -0.06
    oker
    -0.06
    .IsEmpty
    -0.06
    .Compile
    -0.06
    .Enums
    -0.06
    .unregister
    -0.06
    POSITIVE LOGITS
     others
    0.16
     many
    0.15
     other
    0.13
    others
    0.12
    many
    0.11
    Others
    0.11
    'autres
    0.10
     Others
    0.10
     countless
    0.10
    许å¤ļ
    0.09
    Activations Density 0.013%

    No Known Activations