© 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. 105758
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and systems designed for operational efficiency

    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
    conti
    -0.07
    olland
    -0.06
    æĮ¯ãĤĬ
    -0.06
    ypy
    -0.06
    kelas
    -0.06
    arrant
    -0.06
    оза
    -0.06
     civilian
    -0.06
     sel
    -0.05
     amateur
    -0.05
    POSITIVE LOGITS
     field
    0.08
     Field
    0.08
     FieldType
    0.08
     FIELD
    0.08
    _Field
    0.07
     íĺĦ
    0.07
     mobile
    0.07
    Field
    0.07
    .field
    0.07
     windshield
    0.07
    Activations Density 0.018%

    No Known Activations