© 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. 22-LLAMASCOPE-RES-131K
    11. 3742
    Prev
    Next
    INDEX
    Explanations

    instances of the word "came."

    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
    ates
    -0.08
     Brief
    -0.07
    οÏįÏĤ
    -0.07
     remot
    -0.07
    imary
    -0.07
    rette
    -0.07
    ship
    -0.07
    baugh
    -0.06
    odore
    -0.06
    atical
    -0.06
    POSITIVE LOGITS
     via
    0.07
     comes
    0.07
     during
    0.07
     when
    0.07
     came
    0.07
    imir
    0.07
    comes
    0.07
    _via
    0.07
    XT
    0.07
     fast
    0.07
    Activations Density 0.016%

    No Known Activations