© 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. 70720
    Prev
    Next
    INDEX
    Explanations

    subjective statements about individual experiences or beliefs

    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
    anca
    -0.08
    ÏĨι
    -0.07
    ÏĢει
    -0.07
    appen
    -0.07
    abwe
    -0.07
     Cone
    -0.07
    оÑĢÑĭ
    -0.07
    activex
    -0.07
    leted
    -0.07
    edback
    -0.07
    POSITIVE LOGITS
     Boeh
    0.06
     "
    0.06
     never
    0.06
    eyin
    0.06
    .hasNext
    0.06
     favors
    0.06
     fav
    0.06
     Cry
    0.05
    ario
    0.05
     green
    0.05
    Activations Density 0.052%

    No Known Activations