© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106728
    Prev
    Next
    INDEX
    Explanations

    phrases indicating slow progress or concern, particularly related to vaccination efforts and economic trends

    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
    weather
    -0.07
    skirts
    -0.06
     når
    -0.06
     skirts
    -0.06
    iaux
    -0.06
    aux
    -0.06
     titled
    -0.06
    ãĤĵãģ§
    -0.06
    --↵
    -0.06
    apos
    -0.06
    POSITIVE LOGITS
     everywhere
    0.13
     across
    0.13
    Across
    0.11
     Across
    0.11
     chez
    0.09
     wherever
    0.09
     nationwide
    0.08
     worldwide
    0.08
     Everywhere
    0.08
     Ward
    0.07
    Activations Density 0.039%

    No Known Activations