© 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. 9-LLAMASCOPE-RES-131K
    11. 95913
    Prev
    Next
    INDEX
    Explanations

    themes related to radicalism and revolutionary ideas

    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
    manship
    -0.08
    ìĹŃ
    -0.08
    ese
    -0.07
    edo
    -0.07
    oria
    -0.07
    /read
    -0.07
    thing
    -0.07
    eming
    -0.07
    ee
    -0.07
    tle
    -0.06
    POSITIVE LOGITS
    oul
    0.08
    mente
    0.08
    /ext
    0.07
    ziej
    0.07
    ized
    0.07
    ulous
    0.07
    amente
    0.07
    arin
    0.07
     Sang
    0.07
     Thumb
    0.06
    Activations Density 0.006%

    No Known Activations