© 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. 9-LLAMASCOPE-RES-131K
    11. 94992
    Prev
    Next
    INDEX
    Explanations

    instances of emojis and punctuation in 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
    iti
    -0.07
    /welcome
    -0.06
    _firestore
    -0.06
     onCancelled
    -0.06
     Waters
    -0.06
    å¹»
    -0.06
    converted
    -0.06
    lical
    -0.06
    anke
    -0.06
    /o
    -0.06
    POSITIVE LOGITS
    ifest
    0.07
    cq
    0.07
    usz
    0.06
    _OID
    0.06
    czy
    0.06
    /package
    0.06
    _DH
    0.06
    ëĵ
    0.06
    kö
    0.06
    ÏĥÏĦα
    0.06
    Activations Density 0.001%

    No Known Activations