© 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. 118075
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases that evoke strong emotional or opinionated responses

    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
    ż
    -0.06
    ...↵
    -0.06
    olson
    -0.06
    pz
    -0.06
     consum
    -0.06
    ž
    -0.06
    uki
    -0.06
    the
    -0.06
    @s
    -0.05
    ä¼
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĥī
    0.08
    ereo
    0.08
    LookAndFeel
    0.07
    .updateDynamic
    0.07
     itself
    0.07
    lam
    0.07
    åįĴ
    0.07
    ónico
    0.07
    oola
    0.07
    аÑİ
    0.07
    Activations Density 0.018%

    No Known Activations