© 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. 56055
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions indicating connections or relationships between concepts

    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
    dge
    -0.09
     polož
    -0.08
    olle
    -0.07
    ---</
    -0.07
    owan
    -0.07
    бо
    -0.07
    (Of
    -0.07
    quelle
    -0.07
     eius
    -0.07
    VERR
    -0.07
    POSITIVE LOGITS
    /or
    0.07
    usz
    0.06
    itas
    0.06
     Icon
    0.06
    atur
    0.06
    ets
    0.06
    705
    0.06
    и
    0.06
    CAA
    0.06
     Summers
    0.06
    Activations Density 0.068%

    No Known Activations