© 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. 15-LLAMASCOPE-RES-131K
    6. 90843
    Prev
    Next
    INDEX
    Explanations

    pronouns and the concept of personal experience or expression

    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
     Jet
    -0.07
    ½
    -0.07
     sit
    -0.07
    ipi
    -0.06
     analogue
    -0.06
    iÄįka
    -0.06
    rq
    -0.06
    CLK
    -0.06
    adiens
    -0.06
    panies
    -0.06
    POSITIVE LOGITS
     WWW
    0.07
    alia
    0.07
    ãĥĸãĥŃ
    0.06
     exact
    0.06
    ople
    0.06
     do
    0.06
    Tier
    0.06
    æł·çļĦ
    0.06
    _done
    0.06
     Tier
    0.06
    Activations Density 0.031%

    No Known Activations