© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40905
    Prev
    Next
    INDEX
    Explanations

    references to social perceptions and community attitudes

    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
    ideon
    -0.09
    ought
    -0.07
    eview
    -0.07
    itou
    -0.07
    itored
    -0.07
    .kode
    -0.07
    astes
    -0.07
    .CreateInstance
    -0.07
    :UIControl
    -0.07
    -Smith
    -0.07
    POSITIVE LOGITS
     either
    0.07
    ehler
    0.06
    either
    0.06
    sequ
    0.06
    ume
    0.06
    jee
    0.06
    OCR
    0.06
     curiosity
    0.06
     dying
    0.06
     congrat
    0.05
    Activations Density 0.020%

    No Known Activations