© 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 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. 71326
    Prev
    Next
    INDEX
    Explanations

    references to simplification and reduction of complexity in various contexts

    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
    irc
    -0.07
    stry
    -0.06
    rowning
    -0.06
    алÑİ
    -0.06
    .toFloat
    -0.06
    kami
    -0.06
    acco
    -0.06
    jin
    -0.06
    WithName
    -0.06
     JMP
    -0.06
    POSITIVE LOGITS
     down
    0.11
    -down
    0.11
     Down
    0.10
    Down
    0.10
    down
    0.10
     DOWN
    0.09
     reduces
    0.09
     reduce
    0.09
     reduction
    0.09
    Reduc
    0.09
    Activations Density 0.036%

    No Known Activations