© 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. 55640
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the idea of "going for" something or pursuing goals

    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
    олов
    -0.07
    uito
    -0.07
    shed
    -0.07
    PTR
    -0.07
    Ïį
    -0.07
     догов
    -0.06
    epar
    -0.06
    _UNUSED
    -0.06
    .datab
    -0.06
    ãģ¦
    -0.06
    POSITIVE LOGITS
     jug
    0.09
     broke
    0.09
    ipi
    0.08
     gold
    0.07
     Jug
    0.07
    aging
    0.06
    WARDED
    0.06
    grab
    0.06
    olon
    0.06
     Camel
    0.06
    Activations Density 0.010%

    No Known Activations