© 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. 15-LLAMASCOPE-RES-131K
    6. 103257
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exclusion or omission of information

    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
    itzer
    -0.07
    orris
    -0.07
    ZR
    -0.07
    ropp
    -0.07
     è
    -0.07
     Hawkins
    -0.07
    kus
    -0.07
    enaire
    -0.07
    ÃĹ↵↵
    -0.06
    NEXT
    -0.06
    POSITIVE LOGITS
     previously
    0.17
     previous
    0.15
     earlier
    0.15
     Previously
    0.12
    Previous
    0.12
     Previous
    0.12
    previous
    0.12
    Previously
    0.12
     Earlier
    0.11
     سابÙĤ
    0.11
    Activations Density 0.024%

    No Known Activations