© 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. 87975
    Prev
    Next
    INDEX
    Explanations

    references to neglect or abandonment of objects

    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
    705
    -0.06
    à¥įà¤
    -0.06
     pii
    -0.06
    çłĶç©¶æīĢ
    -0.06
    ione
    -0.06
    intelligence
    -0.06
     Lav
    -0.06
    leniyor
    -0.06
    ÏĬκ
    -0.06
    709
    -0.06
    POSITIVE LOGITS
     unused
    0.16
     rarely
    0.14
    unused
    0.14
     seldom
    0.14
     Unused
    0.13
    Unused
    0.13
    -unused
    0.13
     dust
    0.11
    eldom
    0.11
     Rare
    0.10
    Activations Density 0.118%

    No Known Activations