© 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. 78864
    Prev
    Next
    INDEX
    Explanations

    inquiries and statements related to COVID-19 testing and its effectiveness

    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
    Ø´Ùħ
    -0.06
    å½ķ
    -0.06
    _equiv
    -0.06
    hiba
    -0.06
    ãĤ¿ãĥ«
    -0.06
    itle
    -0.06
    atrib
    -0.06
    Trigger
    -0.06
     Corpus
    -0.06
    važ
    -0.06
    POSITIVE LOGITS
     early
    0.07
    erli
    0.07
    tracker
    0.06
     Surveillance
    0.06
     trackers
    0.06
     Transmission
    0.06
    _tracker
    0.06
    amo
    0.06
     Humanity
    0.06
    ák
    0.06
    Activations Density 0.007%

    No Known Activations