© 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. 83855
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and interactions

    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
    /Dk
    -0.07
    .medium
    -0.07
    jure
    -0.07
    grily
    -0.06
    оÑģÑĤей
    -0.06
    ernaut
    -0.06
     registrations
    -0.06
     caring
    -0.06
    iÄįka
    -0.06
    aldo
    -0.06
    POSITIVE LOGITS
     hiring
    0.08
     hire
    0.07
     hires
    0.07
    cpy
    0.06
     nec
    0.06
     Ask
    0.06
     Hiring
    0.06
     Nec
    0.06
    /project
    0.06
    Ask
    0.06
    Activations Density 0.058%

    No Known Activations