© 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. 129464
    Prev
    Next
    INDEX
    Explanations

    first-person expressions related to personal experiences or opinions

    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
     tháºŃm
    -0.08
     dokonce
    -0.08
    obao
    -0.07
    çĶļèĩ³
    -0.07
     EVEN
    -0.06
    even
    -0.06
    aybe
    -0.06
    plusplus
    -0.06
     even
    -0.06
    Ķ
    -0.06
    POSITIVE LOGITS
     certainly
    0.10
     definitely
    0.09
    Regardless
    0.08
     Certainly
    0.08
     whatever
    0.08
    Whatever
    0.08
    None
    0.07
     none
    0.07
     whichever
    0.07
     Regardless
    0.07
    Activations Density 0.034%

    No Known Activations