© 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. 119857
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and symbols

    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
     offsetof
    -0.08
    imler
    -0.07
    legg
    -0.07
    prot
    -0.07
    ÙħاÙĦ
    -0.07
    )__
    -0.07
    ulg
    -0.07
    itom
    -0.07
    емон
    -0.07
    .prot
    -0.07
    POSITIVE LOGITS
     Zot
    0.06
    erli
    0.06
    ̣
    0.06
    [top
    0.06
     mainland
    0.06
    rawn
    0.06
    Invoker
    0.05
     congest
    0.05
     Mic
    0.05
     Scout
    0.05
    Activations Density 0.001%

    No Known Activations