© 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. 17295
    Prev
    Next
    INDEX
    Explanations

    phrases and verbs related to obtaining assistance or services

    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
     Lynch
    -0.07
     pomp
    -0.06
    ãĥ©ãĥ³ãĥī
    -0.06
     Courtesy
    -0.06
    aption
    -0.06
    678
    -0.06
    579
    -0.06
    Å¡il
    -0.06
    animation
    -0.06
    ogne
    -0.06
    POSITIVE LOGITS
    acz
    0.07
     reserve
    0.07
     started
    0.06
    arius
    0.06
    SWG
    0.06
     kê
    0.06
     reserves
    0.06
    WN
    0.06
     Reserve
    0.06
    lund
    0.06
    Activations Density 0.017%

    No Known Activations