© 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. 5-LLAMASCOPE-RES-131K
    11. 125472
    Prev
    Next
    INDEX
    Explanations

    mentions of 'w' followed by numeric values or phrases related to weights or measurements

    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
    ¢åįķ
    -0.08
    _codegen
    -0.07
    REM
    -0.07
    wake
    -0.07
    077
    -0.07
    ERSIST
    -0.06
    elem
    -0.06
    lsru
    -0.06
    neys
    -0.06
    ARSER
    -0.06
    POSITIVE LOGITS
     Stam
    0.08
     regards
    0.07
     Establishment
    0.07
    illas
    0.07
     regard
    0.07
    ount
    0.07
     respect
    0.06
    ï¸ı
    0.06
     Stamp
    0.06
    Stamp
    0.06
    Activations Density 0.012%

    No Known Activations