© 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. 119843
    Prev
    Next
    INDEX
    Explanations

    terms related to activism and activists

    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
    ÙĬاÙĨ
    -0.08
    sworth
    -0.08
    pector
    -0.08
    ikan
    -0.08
    acher
    -0.08
    ricks
    -0.07
    -minus
    -0.07
    ahan
    -0.07
    ething
    -0.07
    ingen
    -0.07
    POSITIVE LOGITS
    iveness
    0.08
    ants
    0.07
    uator
    0.07
     Against
    0.06
    /de
    0.06
    uality
    0.06
    UAL
    0.06
    chedulers
    0.06
    522
    0.06
    /pass
    0.06
    Activations Density 0.028%

    No Known Activations