© 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. 17046
    Prev
    Next
    INDEX
    Explanations

    numerical values and comparisons related to performance metrics

    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
    udd
    -0.07
    berger
    -0.07
    kop
    -0.07
    èĺŃ
    -0.06
    ofire
    -0.06
    iÄįe
    -0.06
    bane
    -0.06
    agger
    -0.06
    unden
    -0.06
    rega
    -0.06
    POSITIVE LOGITS
     nÃło
    0.08
    ä¹ĭä¸Ģ
    0.08
     jamais
    0.08
     ever
    0.07
    ruc
    0.07
    =max
    0.07
    alian
    0.06
    umar
    0.06
    PathComponent
    0.06
    lowest
    0.06
    Activations Density 0.029%

    No Known Activations