© 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. 86864
    Prev
    Next
    INDEX
    Explanations

    numerical information and statistics related to contests or competitions

    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
    égor
    -0.07
    antar
    -0.07
    ibel
    -0.07
    èĹ
    -0.07
     Matches
    -0.06
    мÑĸн
    -0.06
    ippet
    -0.06
    763
    -0.06
     strictly
    -0.06
    Strict
    -0.06
    POSITIVE LOGITS
    obo
    0.07
    uzzi
    0.06
    овиÑĩ
    0.06
     reaff
    0.06
    -Line
    0.06
    _va
    0.05
    RICS
    0.05
    eward
    0.05
    olls
    0.05
    боÑĢ
    0.05
    Activations Density 0.000%

    No Known Activations