© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16054
    Prev
    Next
    INDEX
    Explanations

    instances of redundancy or repetition in descriptions

    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
     surrogate
    -0.06
     shame
    -0.06
     Shame
    -0.06
    tr
    -0.06
    ches
    -0.06
     Mobil
    -0.06
    oph
    -0.06
     real
    -0.06
     sag
    -0.05
    eid
    -0.05
    POSITIVE LOGITS
     among
    0.13
    among
    0.13
     amongst
    0.12
    ä¹ĭä¸Ģ
    0.12
     Among
    0.11
     ÑģÑĢеди
    0.11
    Among
    0.11
    mere
    0.09
     оÑĩеÑĢед
    0.09
    ýš
    0.08
    Activations Density 0.034%

    No Known Activations