© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 131037
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols related to the structure and organization of 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
    zon
    -0.07
    ulp
    -0.07
    alo
    -0.07
    rosso
    -0.07
    903
    -0.07
    zd
    -0.07
    rou
    -0.07
    geh
    -0.07
    osto
    -0.06
    oldur
    -0.06
    POSITIVE LOGITS
    eki
    0.07
    ioned
    0.07
     Vil
    0.06
    LEGRO
    0.06
    ieber
    0.06
    ebra
    0.06
    olen
    0.06
     fres
    0.06
    WT
    0.05
    468
    0.05
    Activations Density 0.004%

    No Known Activations