© 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. 61040
    Prev
    Next
    INDEX
    Explanations

    references to misinformation and false claims surrounding political events

    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
    Âı
    -0.07
    opard
    -0.07
    arkin
    -0.07
    çĬ¬
    -0.06
    민
    -0.06
    annonce
    -0.06
     DEAL
    -0.06
     hypoc
    -0.06
     Moran
    -0.06
    <pre
    -0.06
    POSITIVE LOGITS
    uraa
    0.07
     linking
    0.07
     èģ
    0.06
    uien
    0.06
     Foo
    0.06
    hoo
    0.06
    IH
    0.06
    undo
    0.06
     about
    0.06
     Gard
    0.06
    Activations Density 0.042%

    No Known Activations