© 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. 74575
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Flint," particularly in relation to events or topics associated with the city

    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
    mux
    -0.07
    edly
    -0.06
    OUNDS
    -0.06
    venues
    -0.06
    .aws
    -0.06
    jde
    -0.06
    _fds
    -0.06
    HITE
    -0.06
    zv
    -0.06
    _slave
    -0.06
    POSITIVE LOGITS
     Fl
    0.09
    (Fl
    0.09
    .Fl
    0.09
     fl
    0.08
    chart
    0.08
    Fl
    0.08
    ulence
    0.07
    /fl
    0.07
    anagan
    0.07
    onium
    0.07
    Activations Density 0.055%

    No Known Activations