© 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. 83896
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal opinions, beliefs, and recommendations

    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
    oretical
    -0.07
    ายà¸Ļ
    -0.07
    олаг
    -0.07
    åŃĺäºİ
    -0.07
    rico
    -0.06
    .ul
    -0.06
    ีà¸ŀ
    -0.06
    readcr
    -0.06
    одо
    -0.06
    orrh
    -0.06
    POSITIVE LOGITS
     personally
    0.08
     thoughts
    0.07
     think
    0.07
     Observ
    0.07
    ONGL
    0.07
     recommend
    0.06
    .fits
    0.06
    cki
    0.06
     thinks
    0.06
    éĻĨ
    0.06
    Activations Density 0.023%

    No Known Activations