© 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. 126185
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the idea of support or facilitation for international cooperation

    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
     mesel
    -0.08
    enda
    -0.07
    andr
    -0.07
    ekli
    -0.07
     (('
    -0.07
    γκα
    -0.07
    ovel
    -0.07
    adel
    -0.07
    (æľĪ
    -0.07
    ikler
    -0.07
    POSITIVE LOGITS
     many
    0.07
    utherford
    0.06
     for
    0.06
    оÑĢÑĥ
    0.06
    plied
    0.06
    hof
    0.06
     various
    0.06
     sorts
    0.06
     forces
    0.06
     some
    0.06
    Activations Density 0.047%

    No Known Activations