© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    instances of impending changes or transitions

    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
    ulk
    -0.07
    oha
    -0.06
    izzo
    -0.06
    atch
    -0.06
    irm
    -0.06
    iper
    -0.06
    ette
    -0.06
    egg
    -0.06
    elden
    -0.06
     Manuals
    -0.06
    POSITIVE LOGITS
    portun
    0.07
     Borough
    0.07
    (ib
    0.06
     xúc
    0.06
     Jewish
    0.06
    _ticks
    0.06
     Auschwitz
    0.06
    angen
    0.06
    à¥ģश
    0.06
    .protobuf
    0.06
    Activations Density 0.000%

    No Known Activations