© 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. 55256
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest attempts or recommendations to take action

    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
    adox
    -0.07
    iais
    -0.07
    ories
    -0.06
    ITT
    -0.06
     simples
    -0.06
    ãĥ¼ãĥŀ
    -0.06
     í
    -0.06
    ua
    -0.06
    _EXTERN
    -0.06
    actionDate
    -0.06
    POSITIVE LOGITS
    Ral
    0.07
     algun
    0.07
    643
    0.07
    ëĿ¼ëıĦ
    0.07
    kowski
    0.07
    ÙĪاء
    0.07
     nÃło
    0.07
    émon
    0.07
    azon
    0.06
    با
    0.06
    Activations Density 0.015%

    No Known Activations