© 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. 87950
    Prev
    Next
    INDEX
    Explanations

    mentions of external references and links in the text

    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
    UBY
    -0.07
     Sort
    -0.07
    ertino
    -0.06
    IFO
    -0.06
     sorts
    -0.06
    cro
    -0.06
    ãģ¨ãģĵãĤį
    -0.06
    presso
    -0.06
    368
    -0.06
    autoload
    -0.06
    POSITIVE LOGITS
    ismus
    0.07
     ÙĪÛĮÚ©ÛĮ
    0.07
    otti
    0.07
    exion
    0.06
    ils
    0.06
    xBA
    0.06
    allows
    0.06
     Stall
    0.06
    angs
    0.06
    ovit
    0.06
    Activations Density 0.003%

    No Known Activations