© 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. 5-LLAMASCOPE-RES-131K
    11. 126810
    Prev
    Next
    INDEX
    Explanations

    phrases expressing belief or skepticism

    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
    ovny
    -0.07
    ervices
    -0.07
    vanished
    -0.07
    oders
    -0.06
    ilters
    -0.06
    ics
    -0.06
    elman
    -0.06
    uffers
    -0.06
    ìħĺ
    -0.06
    mán
    -0.06
    POSITIVE LOGITS
    ordes
    0.07
     macro
    0.06
     èĩªåĬ¨çĶŁæĪIJ
    0.06
    fea
    0.06
     ضÙħÙĨ
    0.06
    ξε
    0.06
     Johnston
    0.06
    kyt
    0.06
    .za
    0.05
     wholesale
    0.05
    Activations Density 0.016%

    No Known Activations