© 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. 17-LLAMASCOPE-RES-131K
    11. 127580
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential issues or risks in programming or technical contexts

    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
    ãĥ¼ãĥŃ
    -0.07
     dy
    -0.06
    Äįka
    -0.06
    steller
    -0.06
    asto
    -0.06
    .btnCancel
    -0.06
    pector
    -0.06
     Dy
    -0.06
    PPP
    -0.06
    arella
    -0.06
    POSITIVE LOGITS
    enty
    0.06
    iras
    0.06
    173
    0.06
     separate
    0.06
    ëĵĿ
    0.06
     dedicated
    0.06
    ((&
    0.06
    erras
    0.06
    bart
    0.06
    imd
    0.06
    Activations Density 0.020%

    No Known Activations