© 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. 107168
    Prev
    Next
    INDEX
    Explanations

    references to political movements and societal change

    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
    ::*
    -0.07
    igner
    -0.07
    acier
    -0.07
    rika
    -0.06
    eca
    -0.06
    pdata
    -0.06
    alle
    -0.06
    enko
    -0.06
    ábado
    -0.06
    ripple
    -0.06
    POSITIVE LOGITS
     synonym
    0.07
    untu
    0.07
    725
    0.06
    atak
    0.06
    chet
    0.06
    @brief
    0.06
    ãģ«ãĤĪãĤĭ
    0.06
    :
    0.06
     when
    0.06
     explo
    0.06
    Activations Density 0.091%

    No Known Activations