© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76743
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "chen" and related endings in words

    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
    hack
    -0.07
    inyin
    -0.07
    qv
    -0.06
    aq
    -0.06
    ght
    -0.06
     cheats
    -0.06
    ament
    -0.06
    _checkpoint
    -0.06
    PLIED
    -0.06
     cheat
    -0.06
    POSITIVE LOGITS
    opper
    0.09
    à¥įà¤Ľ
    0.09
    vron
    0.09
    á»ĵng
    0.09
    allenge
    0.08
    rtl
    0.08
    arters
    0.08
    ivement
    0.08
    à¥įà¤ļ
    0.08
    ouser
    0.07
    Activations Density 0.054%

    No Known Activations