© 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 EvalsExportsinterp-engineNEWAPI 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. 87565
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation that express emphasis or excitement

    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
    stem
    -0.07
     cro
    -0.06
    acro
    -0.06
    reira
    -0.06
     Cro
    -0.06
    ylland
    -0.05
    ichert
    -0.05
    isible
    -0.05
    oph
    -0.05
     Madd
    -0.05
    POSITIVE LOGITS
    ORY
    0.07
    efd
    0.07
    太éĥİ
    0.07
    æIJ
    0.07
     hud
    0.07
    Ñı
    0.07
    ÑĢÑĥÑĤ
    0.07
    reeze
    0.07
    iev
    0.07
    UDO
    0.07
    Activations Density 0.003%

    No Known Activations