© 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. 22-LLAMASCOPE-RES-131K
    11. 3843
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that engage the reader

    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
    chg
    -0.06
    obec
    -0.06
     opt
    -0.06
     Vog
    -0.06
    ÏĢη
    -0.06
    ëĬIJ
    -0.05
    shan
    -0.05
     forbidden
    -0.05
    ANE
    -0.05
    LOPT
    -0.05
    POSITIVE LOGITS
     haven
    0.20
     hasn
    0.19
     Haven
    0.16
    haven
    0.16
     hadn
    0.14
     chÆ°a
    0.13
     belum
    0.12
     missed
    0.11
    å°ļ
    0.10
    ãģ¾ãģł
    0.10
    Activations Density 0.016%

    No Known Activations